© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99236
    Prev
    Next
    INDEX
    Explanations

    as-spun, as-new, as obtained

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires whenever it sees the standalone word “as.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    the comparative/subordinating conjunction used to introduce clauses or comparisons, including when capitalized at sentence starts or used as a hyphenated prefix.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    the word "as" when it appears in formal, technical, or transitional contexts (particularly in scientific writing, specifications, or formal statements).

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     тысяч
    -0.77
     黄
    -0.76
     Мексика
    -0.73
     których
    -0.73
    ionale
    -0.72
     Regard
    -0.72
    잤
    -0.72
    Gün
    -0.71
    预约
    -0.71
     aseguró
    -0.70
    POSITIVE LOGITS
     delivered
    1.90
     constructed
    1.60
     received
    1.52
     purchased
    1.50
     installed
    1.46
    delivered
    1.45
     built
    1.44
     written
    1.38
     shipped
    1.37
     issued
    1.36
    Activations Density 0.065%

    No Known Activations