© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 44177
    Prev
    Next
    INDEX
    Explanations

    public keyword

    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
    $
    -2.53
     that
    -2.48
     and
    -2.41
     münchen
    -1.95
    .
    -1.80
     発売
    -1.80
    0
    -1.78
    푣
    -1.76
     köln
    -1.74
     armario
    -1.71
    POSITIVE LOGITS
    饧
    2.39
     has
    2.17
     conscientes
    1.98
    颯
    1.94
    閙
    1.91
     consideradas
    1.91
    癭
    1.88
     are
    1.88
    ዌ
    1.85
     tornou
    1.84
    Activations Density 0.045%

    No Known Activations