© 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. 218024
    Prev
    Next
    INDEX
    Explanations

    come visit

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

    amazon warrior woman

    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
    Negative Logits
    成立
    0.53
    -
    0.52
    ,
    0.49
    ণ
    0.46
    得出
    0.46
    ajal
    0.45
    ;
    0.44
    Te
    0.43
     sights
    0.43
     Song
    0.43
    POSITIVE LOGITS
     کار
    0.54
     enfants
    0.54
     カー
    0.52
     かわいい
    0.51
    ಲ್ಲಿ
    0.50
     بچہ
    0.50
     தனிநாயகம்
    0.49
     vampires
    0.47
     termites
    0.47
     inglés
    0.47
    Activations Density 0.000%

    No Known Activations