© 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. 224700
    Prev
    Next
    INDEX
    Explanations

    owned by

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

    handling parentheses or specific words

    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
    '))->
    0.47
    ెర
    0.47
     Persistence
    0.46
     Join
    0.46
     comandos
    0.44
    選手
    0.43
    ートン
    0.43
    sberg
    0.42
    餘
    0.42
     Utils
    0.42
    POSITIVE LOGITS
    RBI
    0.48
     fanciful
    0.47
    verkehr
    0.47
     falle
    0.46
     барои
    0.46
     profusely
    0.46
    łych
    0.46
    Espagne
    0.46
     կար
    0.46
    ום
    0.45
    Activations Density 0.000%

    No Known Activations