© 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. 191217
    Prev
    Next
    INDEX
    Explanations

    following clauses or phrases

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

    new connection, established communities

    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
    ست
    0.65
    די
    0.54
    Ast
    0.48
    ટ
    0.48
    חל
    0.47
    시다
    0.46
    染
    0.46
    Helen
    0.45
    থ
    0.45
    稔
    0.45
    POSITIVE LOGITS
     infestations
    0.54
    fang
    0.52
     निचे
    0.52
     आगे
    0.49
     Далее
    0.48
     emblems
    0.47
     Firstly
    0.46
     Если
    0.46
     Selanjutnya
    0.46
     വിഷ
    0.46
    Activations Density 0.000%

    No Known Activations