© 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. 158992
    Prev
    Next
    INDEX
    Explanations

    judge other, as permitted

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

    breaking down files or tests

    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
    ի
    0.56
     университета
    0.52
     добра
    0.51
    тон
    0.51
    ティ
    0.50
    тона
    0.50
    ڕۆ
    0.49
    τρα
    0.48
    の
    0.48
    хоро
    0.48
    POSITIVE LOGITS
     खेलकर
    0.51
    ziff
    0.46
    ठबंधन
    0.44
     leverage
    0.44
     wett
    0.41
     matchup
    0.41
    ্যান
    0.40
     megaphone
    0.40
     neutralization
    0.40
    lays
    0.40
    Activations Density 0.000%

    No Known Activations