© 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. 96656
    Prev
    Next
    INDEX
    Explanations

    time and duration

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

    groups of muscles

    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
    一丝
    0.52
    았던
    0.49
     rampant
    0.48
     البدايه
    0.47
    🔼
    0.45
    찧
    0.45
    ոլ
    0.45
    匡
    0.45
    捣
    0.44
    იკ
    0.44
    POSITIVE LOGITS
     groups
    0.54
     metros
    0.53
     mixes
    0.52
     配置
    0.52
     Trebuie
    0.52
     EDU
    0.49
     infant
    0.49
     password
    0.48
     Groups
    0.48
     grupos
    0.48
    Activations Density 0.000%

    No Known Activations