© 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. 2102
    Prev
    Next
    INDEX
    Explanations

    code structure and keywords

    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_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
     बैटरी
    1.01
     leth
    1.01
     بمع
    0.98
    実
    0.92
     عرف
    0.92
    deviation
    0.91
    杳
    0.90
     அழை
    0.86
    incerely
    0.86
    祚
    0.86
    POSITIVE LOGITS
    äub
    0.76
     tôt
    0.73
    新的
    0.73
    ρω
    0.72
    смотрите
    0.72
     паке
    0.70
    Organization
    0.68
     ""))
    0.67
    ⒏
    0.67
    PHEN
    0.67
    Activations Density 0.102%

    No Known Activations