© 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. 149282
    Prev
    Next
    INDEX
    Explanations

    user replaceable parts and preferences

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

    states of being or conditions

    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
    ܠܐ
    0.55
     লুকিয়ে
    0.48
    flakes
    0.47
    OCCO
    0.47
    פים
    0.46
    ાર્થી
    0.46
    臓
    0.45
     mythological
    0.45
    dive
    0.44
    이라고
    0.44
    POSITIVE LOGITS
     Colonial
    0.50
     склон
    0.47
     batsman
    0.45
     colonists
    0.43
    0.42
     Since
    0.42
     Scarborough
    0.40
    бак
    0.40
     actions
    0.40
     seventeenth
    0.39
    Activations Density 0.001%

    No Known Activations