© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 41210
    Prev
    Next
    INDEX
    Explanations

    numerical ranges expressed with to

    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
     it
    -1.79
     from
    -1.77
    to
    -1.67
    .
    -1.66
    up
    -1.64
     What
    -1.62
     I
    -1.57
    on
    -1.54
    and
    -1.53
    It
    -1.52
    POSITIVE LOGITS
    Veu
    1.76
    ឪ
    1.72
    </em>
    1.71
    ケモン
    1.65
    '][
    1.64
    こんばん
    1.63
     ejemplos
    1.62
    ']);
    1.61
    先週
    1.61
    좡
    1.59
    Activations Density 0.044%

    No Known Activations