© 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. 144962
    Prev
    Next
    INDEX
    Explanations

    cookie usage and website policies

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

    common attack vectors

    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
    ;
    0.49
     heifers
    0.48
     kammam
    0.44
     IUnary
    0.43
     çoc
    0.43
     zil
    0.43
     dziecka
    0.42
     stifle
    0.42
     dř
    0.42
     pout
    0.41
    POSITIVE LOGITS
    Haupt
    0.53
    퐁
    0.52
     Englisch
    0.52
    ل
    0.52
     researched
    0.51
    Bali
    0.50
     principaux
    0.50
    방
    0.49
    현
    0.49
    ම
    0.49
    Activations Density 0.000%

    No Known Activations