© 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. 35541
    Prev
    Next
    INDEX
    Explanations

    amount, fees, main, movement, 6, 7, b, L, x, q

    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
    geç
    -0.95
    karakter
    -0.94
     internetowa
    -0.93
    detek
    -0.90
     Vergnügen
    -0.87
    جير
    -0.87
    RAHAM
    -0.87
    katakan
    -0.87
    gantian
    -0.86
    Ưu
    -0.86
    POSITIVE LOGITS
     -----
    0.90
    dite
    0.85
     الأطفال
    0.85
    g
    0.85
    amp
    0.85
    z
    0.84
     antiguo
    0.83
     חבר
    0.83
     椅子
    0.81
    mäßigen
    0.81
    Activations Density 0.333%

    No Known Activations