© 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. 25182
    Prev
    Next
    INDEX
    Explanations

    Excel file processing

    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
    ش
    0.47
     washers
    0.43
     toán
    0.42
    ш
    0.42
    isjon
    0.41
     없고
    0.40
    ,,
    0.39
    구
    0.39
    Offset
    0.39
    학생
    0.39
    POSITIVE LOGITS
    うる
    0.50
     улы
    0.48
     любить
    0.47
    स्वी
    0.44
     margarita
    0.44
     решать
    0.44
     решению
    0.44
    ።
    0.43
     permiss
    0.43
     Laure
    0.43
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.