© 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. 6665
    Prev
    Next
    INDEX
    Explanations

    URLs and code snippets

    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
    2
    -2.84
    le
    -2.53
    '
    -2.33
    is
    -2.31
    You
    -2.30
    $
    -2.30
    al
    -2.20
    for
    -2.17
    {'
    -2.13
    Your
    -2.09
    POSITIVE LOGITS
    archiwizowane
    2.27
     “
    2.03
    鼍
    2.02
     constantemente
    2.00
     aisladas
    1.96
    ⻬
    1.91
     refugi
    1.89
    居る
    1.88
    mitsubishi
    1.88
     vê
    1.88
    Activations Density 0.004%

    No Known Activations