© 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. 9362
    Prev
    Next
    INDEX
    Explanations

    doing one's part

    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
     when
    -1.82
    
    -1.71
    aktifkan
    -1.70
    rassing
    -1.70
    owanie
    -1.68
     exportación
    -1.64
     impressive
    -1.62
    颔
    -1.59
     plásticos
    -1.58
    كان
    -1.56
    POSITIVE LOGITS
    s
    2.38
    on
    1.95
    ',
    1.86
     "
    1.83
    ar
    1.78
    au
    1.73
    5
    1.72
     fosters
    1.70
    6
    1.67
    mu
    1.66
    Activations Density 0.009%

    No Known Activations