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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 328
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     রূপান্তরিত
    1.52
     En
    1.43
     EN
    1.41
     principales
    1.38
    uals
    1.37
     অনার্স
    1.37
    ’
    1.36
    aux
    1.35
     documentary
    1.31
    ástico
    1.29
    POSITIVE LOGITS
    ifiably
    1.75
    тю
    1.67
    ']*
    1.66
    تف
    1.65
    <bos>
    1.64
    تج
    1.62
     "\\"
    1.61
    िया
    1.57
    ితే
    1.55
    تون
    1.54
    Activations Density 2.116%

    No Known Activations