© 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. 10-GEMMASCOPE-RES-131K
    7. 113921
    Prev
    Next
    INDEX
    Explanations

    language codes or path segments

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

    file path separators in import statements and module references.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     all
    -2.55
     using
    -2.41
     during
    -2.28
     while
    -2.16
     and
    -2.16
     changed
    -2.13
     after
    -2.13
     from
    -2.11
     as
    -2.05
     had
    -2.02
    POSITIVE LOGITS
     rése
    2.11
    着一个
    1.98
     trám
    1.98
     réve
    1.91
    泚
    1.90
     perpé
    1.89
     alho
    1.87
     😁
    1.85
     régal
    1.85
     tém
    1.80
    Activations Density 0.016%

    No Known Activations