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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 26021
    Prev
    Next
    INDEX
    Explanations

    on [day of week]

    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
    new
    -1.07
     Sieger
    -1.02
    '}';
    -1.02
     okaz
    -1.00
     "'");
    -0.97
    точно
    -0.96
    pherals
    -0.96
    tenths
    -0.91
     have
    -0.91
    口
    -0.91
    POSITIVE LOGITS
     餐厅
    1.05
    تاریخ
    0.99
    すっ
    0.98
    うつ
    0.94
    ドキドキ
    0.92
     historische
    0.91
    élimin
    0.91
    スペック
    0.90
    あっという
    0.90
    さぁ
    0.90
    Activations Density 0.028%

    No Known Activations