© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 14046
    Prev
    Next
    INDEX
    Explanations

    create or adoption

    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
    (/
    0.99
     EL
    0.96
    ♪
    0.95
    PR
    0.94
    (#
    0.94
     governing
    0.93
    ┌
    0.90
    *)
    0.90
    ?>
    0.90
    '
    0.88
    POSITIVE LOGITS
     wymag
    1.29
    <unused333>
    1.18
     vecin
    1.18
     schwier
    1.15
     difficile
    1.15
     wszystkie
    1.13
     temporadas
    1.13
     неделю
    1.11
     procedura
    1.10
     sonuc
    1.10
    Activations Density 0.000%

    No Known Activations