© 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. 127564
    Prev
    Next
    INDEX
    Explanations

    beginning phrases

    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
     you
    -2.22
     your
    -2.14
     geschikt
    -1.63
     beſt
    -1.62
     descendre
    -1.57
     ſtre
    -1.49
     juſt
    -1.48
     firſt
    -1.47
     toalla
    -1.46
    itting
    -1.41
    POSITIVE LOGITS
     but
    1.74
    趼
    1.62
    有多
    1.45
    引用元
    1.44
    那些
    1.41
    мл
    1.41
    ное
    1.40
     Although
    1.38
    нс
    1.37
    姥
    1.36
    Activations Density 0.000%

    No Known Activations