© 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. 212210
    Prev
    Next
    INDEX
    Explanations

    corvette fuse BALL BOX

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

    GitHub, hurts, profile, much

    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
    פּ
    0.52
    ))+
    0.48
    Biografia
    0.47
     XLSX
    0.47
     nuevos
    0.46
    RELATES
    0.46
    境界層
    0.45
    راجعه
    0.44
    Buen
    0.43
    Reviews
    0.43
    POSITIVE LOGITS
    to
    0.50
     δημο
    0.48
    誕
    0.47
    べて
    0.47
     だけ
    0.47
    ffi
    0.46
    ドイツ
    0.46
     historically
    0.45
     cặp
    0.45
     regularly
    0.45
    Activations Density 0.001%

    No Known Activations