© 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. 69
    Prev
    Next
    INDEX
    Explanations

    magnitude and importance

    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
    ুজ
    2.12
    િયા
    2.10
    span
    1.99
    வும்
    1.88
    艰
    1.87
    shy
    1.83
    ا
    1.75
    ेंग
    1.73
    l
    1.68
     कार
    1.67
    POSITIVE LOGITS
    babel
    2.09
    ultats
    1.99
    idated
    1.84
    𝐯
    1.84
    anthemum
    1.81
     bør
    1.78
     مطلق
    1.77
    utzen
    1.76
    чыць
    1.76
    nextInt
    1.75
    Activations Density 3.941%

    No Known Activations