© 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. 113886
    Prev
    Next
    INDEX
    Explanations

    reading data structures

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

    the dot operator used for method calls and property access in programming code.

    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
     which
    -2.08
     and
    -1.77
    ありません
    -1.59
     while
    -1.56
     not
    -1.53
     though
    -1.52
     see
    -1.50
     also
    -1.49
     do
    -1.45
    </h5>
    -1.45
    POSITIVE LOGITS
    فيلم
    1.63
    provides
    1.48
    媖
    1.44
    前回
    1.43
     grosir
    1.41
     actuels
    1.38
    xiii
    1.38
    seemed
    1.37
    indicate
    1.34
     last
    1.34
    Activations Density 0.048%

    No Known Activations