© 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. 15470
    Prev
    Next
    INDEX
    Explanations

    physical properties of matter

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     herbes
    -1.55
     horrid
    -1.54
    蟊
    -1.49
    🫅
    -1.48
     dreadful
    -1.47
     jarring
    -1.45
     miſ
    -1.45
    你是不是
    -1.45
     alcuni
    -1.44
     vielen
    -1.42
    POSITIVE LOGITS
     both
    2.09
     all
    1.86
    Both
    1.67
     fifteen
    1.59
     at
    1.52
     sowohl
    1.51
     with
    1.49
     partially
    1.48
     thirteen
    1.45
     mostly
    1.45
    Activations Density 0.419%

    No Known Activations