© 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. 204731
    Prev
    Next
    INDEX
    Explanations

    religious and protective contexts

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

    Amphibians, peel, syntax, selling

    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
    k
    0.46
    kinase
    0.46
    apopt
    0.42
    pane
    0.42
    াবা
    0.42
    一百
    0.42
     फांसी
    0.42
    ER
    0.41
    Bom
    0.41
     io
    0.41
    POSITIVE LOGITS
     Phil
    0.50
    ت
    0.50
    🚻
    0.49
    👞
    0.47
     Couples
    0.47
     desenc
    0.46
     приорите
    0.46
     Zweck
    0.46
    лія
    0.45
    थम
    0.45
    Activations Density 0.000%

    No Known Activations