© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 73606
    Prev
    Next
    INDEX
    Explanations

    genetic diversity or let me

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

    commas in code contexts, especially following Component declarations or within function parameter lists.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Meksi
    -1.37
     Docteur
    -1.36
     SECOND
    -1.34
     parfü
    -1.33
     babak
    -1.31
     Ministre
    -1.27
     kesi
    -1.27
     akku
    -1.26
     katk
    -1.25
     klinik
    -1.24
    POSITIVE LOGITS
     in
    1.14
    %;
    1.11
     (
    1.09
    (
    1.08
    But
    1.04
     revisar
    1.02
     but
    1.00
     especially
    0.97
    ↵↵
    0.96
    trona
    0.95
    Activations Density 0.003%

    No Known Activations