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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 17-GEMMASCOPE-2-RES-16K
    7. 1591
    Prev
    Next
    INDEX
    Explanations

    scene descriptions and voices

    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
    2.95
     [
    2.60
     -
    2.20
     你
    2.15
     don
    2.15
     <
    2.15
     (
    2.14
     s
    2.12
     ‘
    2.09
     tip
    2.08
    POSITIVE LOGITS
    হইতে
    2.46
    হইবে
    2.45
    NeedConnect
    2.41
     هاکي
    2.41
    Databaze
    2.39
    Tidak
    2.38
    utilizzo
    2.35
    Selain
    2.35
    পূর্ন
    2.34
     लगाएंगे
    2.34
    Activations Density 0.309%

    No Known Activations