© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 20383
    Prev
    Next
    INDEX
    Explanations

    color, image, size attributes

    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
     quando
    -1.97
    瘊
    -1.95
     Of
    -1.93
     was
    -1.91
     -.
    -1.89
     của
    -1.85
     وقال
    -1.84
    埽
    -1.84
     banter
    -1.79
     -"
    -1.75
    POSITIVE LOGITS
    鸯
    2.02
     striving
    1.90
    });*/
    1.84
     memutus
    1.77
    所说
    1.73
     those
    1.72
     includes
    1.72
     assessing
    1.69
     were
    1.68
     preventing
    1.65
    Activations Density 0.003%

    No Known Activations