© 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. 1861
    Prev
    Next
    INDEX
    Explanations

    where

    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
     totalité
    0.81
     pomoć
    0.77
     fact
    0.76
    آور
    0.76
    量
    0.75
    \"]\
    0.74
     //
    0.73
    $\$
    0.72
    及其
    0.72
     olmadığını
    0.72
    POSITIVE LOGITS
     where
    5.22
    where
    4.89
     donde
    4.37
    Where
    4.24
     où
    4.22
     Where
    4.20
     где
    4.17
     WHERE
    4.01
     wher
    3.95
     wherein
    3.89
    Activations Density 1.849%

    No Known Activations