© 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. 111730
    Prev
    Next
    INDEX
    Explanations

    conditions and restrictions

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

    game mechanics, currency, or strategy

    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
    ИН
    0.53
    ཋ
    0.46
     परंपरा
    0.45
     मग
    0.45
    ORDON
    0.43
    ING
    0.43
    लेख
    0.43
    रेखा
    0.43
    麹
    0.43
    цвет
    0.42
    POSITIVE LOGITS
     precluded
    0.49
     precludes
    0.49
     seeking
    0.49
     attempting
    0.49
     soliciting
    0.48
     exclusivement
    0.47
     assess
    0.47
     aucune
    0.47
     assesses
    0.47
     solicitar
    0.46
    Activations Density 0.001%

    No Known Activations