© 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. 94837
    Prev
    Next
    INDEX
    Explanations

    Grade Dance, Citric Acid, started stitching

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

    catalyze, Changes, pipelines, understand, period, Indian

    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
     cyclohexane
    0.49
    いろいろ
    0.49
     সংখ্যা
    0.48
    kWh
    0.46
     batters
    0.46
    mRNA
    0.46
    鬼
    0.44
    শক্তি
    0.44
     RUB
    0.44
     দৃষ্টি
    0.43
    POSITIVE LOGITS
    oka
    0.46
    ى
    0.45
    ジュン
    0.44
    que
    0.43
    atuur
    0.43
    ట్ల
    0.42
    iez
    0.42
    atre
    0.41
    ^{*}}\
    0.41
     impromptu
    0.41
    Activations Density 0.001%

    No Known Activations