© 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. 13-GEMMASCOPE-2-RES-16K
    7. 1044
    Prev
    Next
    INDEX
    Explanations

    technical commands and resources

    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_13_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
     or
    0.95
     and
    0.94
    and
    0.85
     или
    0.76
     hydrate
    0.76
     amount
    0.75
     cylind
    0.75
    ޮ
    0.74
     floated
    0.74
     و
    0.73
    POSITIVE LOGITS
     tiếng
    1.06
     Tư
    1.05
     Koordin
    1.04
     стоковые
    1.02
     naše
    1.01
     Kräfte
    1.00
     Thông
    1.00
     Pau
    0.99
    ViewPager
    0.99
     biên
    0.99
    Activations Density 0.261%

    No Known Activations