© 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. 136707
    Prev
    Next
    INDEX
    Explanations

    dumpster, Lord, finest, Trade, respond

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

    requirements and planning

    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
    Princip
    0.47
    棺
    0.46
     unbear
    0.46
    Registre
    0.46
     infractions
    0.46
    стран
    0.45
     prést
    0.45
    движи
    0.45
    <unused95>
    0.44
    ព័
    0.44
    POSITIVE LOGITS
     ト
    0.55
    </
    0.54
     ت
    0.49
     ท
    0.49
     Node
    0.48
     covers
    0.48
     =
    0.48
     Trade
    0.48
     ร
    0.47
     m
    0.46
    Activations Density 0.000%

    No Known Activations