© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 84767
    Prev
    Next
    INDEX
    Explanations

    dispelling fear or doubt

    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
     も
    -2.00
    躄
    -1.95
     hinder
    -1.77
    飈
    -1.73
            
    -1.73
     dopo
    -1.71
    
    -1.71
    ⚋
    -1.70
    ómico
    -1.70
     sencillas
    -1.69
    POSITIVE LOGITS
    There
    2.06
    ’
    2.03
    ll
    1.97
    ↵
    1.91
    there
    1.85
     ñ
    1.70
    这是一
    1.66
    8
    1.63
    Only
    1.63
    Because
    1.62
    Activations Density 0.001%

    No Known Activations