© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 86771
    Prev
    Next
    INDEX
    Explanations

    differences and variations

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

    The neuron fires on numeric tokens, especially exact quantities or measurements (including decimals).

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

    statements indicating differences, variability, or deviations between compared items, results, or conditions, often in disclaimer-style comparisons.

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

    disclaimers or warnings about potential variations, differences, or discrepancies.

    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_10/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
    狗狗
    -1.41
    tting
    -1.40
    𐬹
    -1.38
    ting
    -1.37
    }
    -1.34
     eran
    -1.33
    ofan
    -1.33
    ystemen
    -1.33
    сль
    -1.32
    punkten
    -1.32
    POSITIVE LOGITS
     when
    1.80
     how
    1.73
     with
    1.73
     until
    1.71
     each
    1.71
     who
    1.64
     this
    1.61
     they
    1.57
     the
    1.56
     what
    1.52
    Activations Density 0.092%

    No Known Activations