© 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. 241134
    Prev
    Next
    INDEX
    Explanations

    other words, fork to, may be

    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
     ポケット
    0.47
     Azi
    0.46
     endpoints
    0.46
     የተቀ
    0.46
     အတွ
    0.45
     並
    0.45
     ダーク
    0.45
     Positions
    0.45
     Oeste
    0.44
     sites
    0.44
    POSITIVE LOGITS
    给他
    0.48
    গের
    0.47
    ตาม
    0.47
    根据
    0.46
    توا
    0.43
    ื
    0.43
     přest
    0.43
    تك
    0.43
    日の
    0.42
    dod
    0.42
    Activations Density 0.002%

    No Known Activations