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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 1439
    Prev
    Next
    INDEX
    Explanations

    making exceptions

    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
     réfugiés
    -1.62
    不仅
    -1.52
    Setiap
    -1.48
    きちんと
    -1.42
     unſ
    -1.41
    除了
    -1.40
    .*/
    -1.39
     vôtre
    -1.38
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -1.36
     prisonniers
    -1.36
    POSITIVE LOGITS
     ofertas
    1.73
     to
    1.71
     their
    1.65
     in
    1.56
     when
    1.56
     during
    1.52
    )("
    1.50
     while
    1.47
     for
    1.47
    </tfoot>
    1.47
    Activations Density 0.036%

    No Known Activations