© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 158813
    Prev
    Next
    INDEX
    Explanations

    political party or group

    np_acts-logits-general · gemini-2.5-flash-lite

    technical terms and explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yng
    0.49
    🧭
    0.49
    jumpa
    0.48
    🏖
    0.48
    rekt
    0.48
     일어나
    0.48
    DanhMuc
    0.48
    simx
    0.48
    浧
    0.47
    starcore
    0.47
    POSITIVE LOGITS
    that
    0.60
     THAT
    0.59
     that
    0.52
     STATISTICS
    0.47
     [
    0.46
    c
    0.46
    ла
    0.45
     IR
    0.45
    compromising
    0.44
     OF
    0.44
    Activations Density 0.000%

    No Known Activations