© 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. 42497
    Prev
    Next
    INDEX
    Explanations

    offering help or aid

    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
    '
    -1.87
     halbe
    -1.41
     equation
    -1.41
    硖
    -1.40
    हर
    -1.33
     Slovensku
    -1.31
    考生
    -1.30
     invasión
    -1.29
    ビット
    -1.29
     bestselling
    -1.29
    POSITIVE LOGITS
    Like
    1.81
    Unfortunately
    1.80
     Nevertheless
    1.77
     ഒ
    1.72
    Unlike
    1.70
    However
    1.67
    This
    1.67
     Unfortunately
    1.63
    There
    1.63
    Those
    1.60
    Activations Density 0.028%

    No Known Activations