© 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. 2224
    Prev
    Next
    INDEX
    Explanations

    Pokemon cards

    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
    勸
    0.44
     índice
    0.42
    ड्ड
    0.40
     layoff
    0.40
    ड्डा
    0.39
    ಸ್ಟ್
    0.38
     filoz
    0.38
     индекс
    0.38
    मत
    0.37
    सरत
    0.37
    POSITIVE LOGITS
     artistic
    0.34
     Geburtstag
    0.34
    (
    0.33
    OO
    0.33
     papier
    0.33
     Artistic
    0.32
     Squares
    0.32
     Technologies
    0.32
    ζ
    0.31
     twilight
    0.31
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.