© 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. 14531
    Prev
    Next
    INDEX
    Explanations

    Museum of Anthropology at UBC

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    йович
    2.68
    พ์
    2.62
     बध
    2.62
     இடைய
    2.61
    িতায়
    2.58
     hindrance
    2.57
    Р
    2.55
     сложно
    2.51
    к
    2.51
    ToPlot
    2.51
    POSITIVE LOGITS
    捉
    2.23
     Egyes
    2.15
     ked
    2.15
     pe
    2.15
    sling
    2.13
    beef
    2.12
     priem
    2.11
    ʃ
    2.09
    sle
    2.06
    <bos>
    2.06
    Activations Density 0.003%

    No Known Activations