© 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. 25355
    Prev
    Next
    INDEX
    Explanations

    if you're

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

    snapshot, Bühne, languages, factions, Hindi

    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
    ED
    0.53
    EX
    0.49
    Cast
    0.46
    en
    0.46
    ul
    0.46
    HON
    0.45
    
    0.45
    in
    0.44
    ナ
    0.44
    AES
    0.44
    POSITIVE LOGITS
    ాత్రి
    0.50
     thú
    0.49
     snapshot
    0.48
    疑問
    0.48
     Bühne
    0.48
     Buds
    0.47
    ัพท์
    0.46
    levelname
    0.46
     достовер
    0.46
     playtime
    0.46
    Activations Density 0.001%

    No Known Activations