© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35315
    Prev
    Next
    INDEX
    Explanations

    questions about why

    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
     ингреди
    -1.86
     ваз
    -1.70
     lecker
    -1.55
     estrelas
    -1.53
    Vä
    -1.51
     géographie
    -1.44
     десер
    -1.41
     tzw
    -1.38
    FlatButton
    -1.37
    อร่อย
    -1.36
    POSITIVE LOGITS
    {*
    1.36
    Ĭ
    1.31
    ♥♥
    1.27
    even
    1.27
     PHILIP
    1.26
    ĭ
    1.25
    😠
    1.22
    🍔
    1.20
    וּ
    1.19
     ivi
    1.17
    Activations Density 0.569%

    No Known Activations