© 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. 22800
    Prev
    Next
    INDEX
    Explanations

    discussing, talking, or negotiating

    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
    Negative Logits
     هناك
    -1.19
    ("}");
    -1.16
    って何
    -1.16
     alguns
    -1.15
     a
    -1.14
    翆
    -1.13
    pæ
    -1.11
    為に
    -1.10
    naruto
    -1.09
    我一
    -1.09
    POSITIVE LOGITS
     only
    1.52
     because
    1.48
     more
    1.35
    When
    1.27
    لاعب
    1.25
     debilitating
    1.23
     discussion
    1.23
    :{},
    1.23
    only
    1.23
     with
    1.21
    Activations Density 0.038%

    No Known Activations