© 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. 2149
    Prev
    Next
    INDEX
    Explanations

    file and folder lists

    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
    java
    0.51
     რო
    0.49
    ole
    0.46
    ť
    0.46
    ਜ
    0.45
    ۔
    0.44
    ate
    0.44
    ã
    0.43
    เจ
    0.43
     थकान
    0.43
    POSITIVE LOGITS
     proclaims
    0.47
     toutefois
    0.45
     attén
    0.44
     delineate
    0.44
     verlei
    0.44
    授予
    0.44
    ذن
    0.43
     auteurs
    0.43
     छैन
    0.43
     vésicules
    0.43
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.