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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 2452
    Prev
    Next
    INDEX
    Explanations

    startup script

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

    The neuron strongly activates on numeric tokens (digits and multi‐digit number sequences).

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

    boilerplate header and attribution text in technical documents or code (e.g., copyright/licensing notices, author credits, and uppercase section headings).

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

    line breaks and whitespace in source code or formatted technical documents.

    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
    👀
    -0.72
    👆
    -0.71
    ಲು
    -0.66
    orz
    -0.66
     Verantwortung
    -0.66
     triples
    -0.66
     operar
    -0.65
     chiffon
    -0.65
    Betyg
    -0.65
     pagination
    -0.64
    POSITIVE LOGITS
     ál
    0.73
    Bras
    0.68
     Ton
    0.66
     다음
    0.63
     players
    0.62
    rivial
    0.61
    綜合報導
    0.61
    =$_
    0.61
    voye
    0.61
     Quar
    0.60
    Activations Density 0.054%

    No Known Activations