© 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. 47539
    Prev
    Next
    INDEX
    Explanations

    required actions

    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
     inspiradoras
    -1.83
    ches
    -1.82
     preocupar
    -1.78
     agujero
    -1.77
     occasions
    -1.76
     Нови
    -1.76
     supreme
    -1.73
    urança
    -1.73
    葙
    -1.72
     sorts
    -1.71
    POSITIVE LOGITS
     and
    2.28
     Its
    2.14
    </td>
    1.95
    𖥧
    1.70
    Its
    1.70
    <b>
    1.69
    which
    1.65
    1.64
    (
    1.62
     Of
    1.59
    Activations Density 0.016%
    No Known Activations