© 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. 26222
    Prev
    Next
    INDEX
    Explanations

    numbers and code elements

    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
    diman
    -0.97
    覧
    -0.93
    ◡
    -0.91
    谞
    -0.90
    alım
    -0.90
    ぐるみ
    -0.89
     Leche
    -0.88
    kursi
    -0.88
    perg
    -0.88
    БЕ
    -0.88
    POSITIVE LOGITS
    了许多
    0.92
    4
    0.91
    lio
    0.91
    2
    0.91
     Уже
    0.90
    mathrm
    0.89
     umfasst
    0.88
     saranno
    0.88
     Многие
    0.88
    ille
    0.87
    Activations Density 0.020%

    No Known Activations