© 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. 1736
    Prev
    Next
    INDEX
    Explanations

    <code>Q</code>, <code>Introduction</code>, <code>If</code> as starts

    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
    \
    -2.56
    The
    -1.90
     dahil
    -1.78
    蓠
    -1.76
     you
    -1.74
    тий
    -1.70
    
    -1.62
    </tfoot>
    -1.61
     hanya
    -1.60
     由
    -1.59
    POSITIVE LOGITS
     numerosos
    1.95
     ligeramente
    1.78
    ↵
    1.77
     berühmten
    1.68
     中身
    1.68
     numerosas
    1.67
     üblichen
    1.67
    droje
    1.67
     verschiedener
    1.66
     echten
    1.66
    Activations Density 0.000%

    No Known Activations