© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 249714
    Prev
    Next
    INDEX
    Explanations

    component contract

    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
    人気
    0.50
    ペ
    0.49
     nœ
    0.49
    人気の
    0.46
    രിക
    0.46
     něco
    0.45
     patina
    0.45
     dafür
    0.45
    携帯
    0.45
     när
    0.45
    POSITIVE LOGITS
    ENSIVE
    0.48
     आईसी
    0.47
    ಡ್
    0.47
    rists
    0.46
    ЕЛЬ
    0.46
     Hourly
    0.46
    ್
    0.46
     ಮಿಶ್ರ
    0.45
     이
    0.45
    篌
    0.45
    Activations Density 0.000%

    No Known Activations