© 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. 251294
    Prev
    Next
    INDEX
    Explanations

    team after

    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
    چار
    0.54
    riculum
    0.51
    鲞
    0.46
    ;
    0.44
     Salmonella
    0.43
    تي
    0.43
    प्लेस
    0.43
    បរ
    0.42
     Henley
    0.42
    )/\
    0.42
    POSITIVE LOGITS
     жі
    0.53
    USED
    0.53
    ू
    0.50
    İ
    0.50
     নারী
    0.50
     במה
    0.50
     なさい
    0.49
    ISHING
    0.49
    IE
    0.48
    ADA
    0.48
    Activations Density 0.000%

    No Known Activations