© 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. 13601
    Prev
    Next
    INDEX
    Explanations

    phenomenological, phenomenon, scenographer

    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
    e
    -3.41
    ܜ
    -2.83
    蕻
    -2.59
    ྵ
    -2.58
    )’
    -2.56
    焄
    -2.52
    ’;
    -2.50
    镔
    -2.48
    ”;
    -2.42
     betek
    -2.41
    POSITIVE LOGITS
    1
    3.19
    2
    2.84
    7
    2.80
    *
    2.73
    4
    2.73
    {
    2.72
    0
    2.66
    或者
    2.59
    9
    2.58
    ,'
    2.48
    Activations Density 0.013%

    No Known Activations