© 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. 22-GEMMASCOPE-RES-131K
    4. 13796
    Prev
    Next
    INDEX
    Explanations

    function arguments and control flow

    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
     basadas
    -0.87
    FINALLY
    -0.86
    {?>
    -0.84
    izaron
    -0.83
    Biographies
    -0.82
    🪩
    -0.81
    lihood
    -0.78
    ologists
    -0.78
    という感じ
    -0.77
    変わらず
    -0.77
    POSITIVE LOGITS
     if
    1.41
     если
    1.22
    必须
    1.10
     must
    1.10
    if
    1.09
     ако
    1.06
    必須
    1.06
     nếu
    1.05
    ต้อง
    1.04
    ถ้า
    0.97
    Activations Density 0.002%

    No Known Activations