© 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. 72297
    Prev
    Next
    INDEX
    Explanations

    government and associated locations

    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
     a
    -2.48
     as
    -2.11
     because
    -1.90
     there
    -1.77
     in
    -1.76
     one
    -1.70
    ໊
    -1.63
    晅
    -1.60
     from
    -1.53
     deutscher
    -1.52
    POSITIVE LOGITS
     vaksin
    1.51
    听得
    1.47
    犛
    1.45
    姈
    1.45
     sorpresa
    1.45
    ㍑
    1.41
    ⸢
    1.41
    ENNE
    1.41
    atisk
    1.40
     любого
    1.38
    Activations Density 0.218%

    No Known Activations