© 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. 119626
    Prev
    Next
    INDEX
    Explanations

    codes containing numbers and symbols

    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
    瓩
    -2.30
     Its
    -2.17
    –
    -1.95
    _
    -1.87
     пройдет
    -1.78
    蜴
    -1.77
    嚶
    -1.75
     begle
    -1.72
    ⎆
    -1.71
     brilliantly
    -1.69
    POSITIVE LOGITS
    鬭
    1.98
     of
    1.88
     soñ
    1.82
    炻
    1.77
     inconvénients
    1.75
    Poloha
    1.70
    yoruz
    1.67
    
    1.66
    ኧ
    1.66
    sieger
    1.63
    Activations Density 0.003%

    No Known Activations