© 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. 22-GEMMASCOPE-RES-131K
    7. 13871
    Prev
    Next
    INDEX
    Explanations

    mathematical formatting symbols

    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_22/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
     when
    -2.08
     if
    -1.98
    ﾚ
    -1.88
     église
    -1.82
     those
    -1.78
    蛧
    -1.77
    ﾛ
    -1.77
    蠱
    -1.70
     pelaksanaan
    -1.67
    してみました
    -1.66
    POSITIVE LOGITS
    '
    2.84
    *
    2.38
    <
    2.17
    --
    2.13
     magnific
    2.11
    {
    2.09
    “
    2.08
    えっ
    2.02
    ...
    1.91
    [
    1.88
    Activations Density 0.001%

    No Known Activations