© 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. 34-GEMMASCOPE-RES-131K
    4. 93895
    Prev
    Next
    INDEX
    Explanations

    code annotations

    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_34/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
     salas
    -0.82
    旗下
    -0.81
     artesan
    -0.80
    цо
    -0.79
     Saal
    -0.79
     Patriots
    -0.78
    flug
    -0.78
     manages
    -0.78
     boleh
    -0.78
     siglas
    -0.77
    POSITIVE LOGITS
    tuy
    0.97
    AFR
    0.90
     arasındaki
    0.89
     TRUTH
    0.88
     ewe
    0.83
    適当
    0.82
     ダーク
    0.81
    Desen
    0.79
    きれい
    0.78
     passing
    0.77
    Activations Density 0.003%

    No Known Activations