© 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. 250475
    Prev
    Next
    INDEX
    Explanations

    Synagogue completions

    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
    そして
    0.53
     政
    0.48
    APC
    0.47
    емов
    0.46
     blatant
    0.46
    ಟ್ರ
    0.46
    犯罪
    0.45
    政
    0.45
    承認
    0.44
     criminality
    0.44
    POSITIVE LOGITS
     inventory
    0.50
     stomachs
    0.50
     skies
    0.47
     water
    0.46
     marine
    0.45
     misspelled
    0.44
     ifstream
    0.44
     spines
    0.43
     unfamiliar
    0.43
     léka
    0.43
    Activations Density 0.001%

    No Known Activations