© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 65825
    Prev
    Next
    INDEX
    Explanations

    circa dates and names

    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
    跸
    -1.98
    ཿ
    -1.91
    薷
    -1.79
    靦
    -1.67
    傒
    -1.62
    茔
    -1.60
     vinilo
    -1.59
    婠
    -1.58
    に行ってきました
    -1.57
    に乗って
    -1.54
    POSITIVE LOGITS
     because
    2.13
     from
    1.76
     Because
    1.69
     with
    1.68
     only
    1.66
     also
    1.60
     by
    1.59
    (
    1.59
     if
    1.51
    Because
    1.51
    Activations Density 0.022%

    No Known Activations