© 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. 48258
    Prev
    Next
    INDEX
    Explanations

    ES6, ES clusters, ES cells

    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
    the
    -3.52
    their
    -3.08
    魮
    -2.95
    ︕
    -2.78
     cartões
    -2.77
    tiously
    -2.75
     the
    -2.75
    ophageal
    -2.69
    豋
    -2.67
     dibanding
    -2.59
    POSITIVE LOGITS
    {
    3.72
    _
    2.86
    独特
    2.52
    <
    2.45
    ↵↵
    2.41
     andere
    2.41
     emphatic
    2.38
     ES
    2.36
     imaginative
    2.36
    ’
    2.33
    Activations Density 0.010%

    No Known Activations