© 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. 17-GEMMASCOPE-2-RES-16K
    7. 629
    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_17_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
    あらゆる
    0.78
    一系列
    0.77
    →
    0.77
     respectivamente
    0.77
     từng
    0.72
     respectively
    0.72
    enuhi
    0.72
    任意の
    0.70
     всеми
    0.70
    =
    0.69
    POSITIVE LOGITS
     thing
    2.19
     drawback
    1.93
     downside
    1.85
     문제는
    1.83
     главное
    1.80
     caveat
    1.78
    重點
    1.67
     problem
    1.59
    Thing
    1.59
     दिक्कत
    1.59
    Activations Density 1.466%

    No Known Activations