© 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. 10-GEMMASCOPE-RES-131K
    7. 110540
    Prev
    Next
    INDEX
    Explanations

    names, dates, or questions

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    <
    -3.92
    *
    -3.08
    ?
    -2.94
     
    -2.91
    <i>
    -2.81
    -
    -2.72
    -,
    -2.67
     It
    -2.64
    but
    -2.59
     —
    -2.59
    POSITIVE LOGITS
     bringe
    2.89
    鈊
    2.81
    櫺
    2.80
     eigene
    2.77
    魴
    2.77
    豋
    2.75
     Anſ
    2.72
    탉
    2.69
    ஂ
    2.69
     放題
    2.66
    Activations Density 0.000%

    No Known Activations