© 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. 150859
    Prev
    Next
    INDEX
    Explanations

    reward for, rubbish pieces, blind kits

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

    beyond legal compliance

    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
     school
    0.52
    GC
    0.48
    WS
    0.47
    UM
    0.46
    ﺭ
    0.46
     তাঁদের
    0.45
     температуры
    0.45
     বছর
    0.44
    IOUS
    0.43
     capital
    0.43
    POSITIVE LOGITS
    akaranam
    0.48
    orak
    0.48
    |।
    0.47
    🠀
    0.45
    﨑
    0.44
    chrane
    0.43
    LookAnd
    0.43
    Gabri
    0.43
    ⤷
    0.43
    pano
    0.42
    Activations Density 0.000%

    No Known Activations