© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 4631
    Prev
    Next
    INDEX
    Explanations

    crucial before understanding

    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
     bikin
    1.95
     booze
    1.94
     cachorro
    1.91
     werewolf
    1.91
     ModInt
    1.90
     sorta
    1.84
    <unused1114>
    1.81
     criaturas
    1.79
     PlayerSelector
    1.78
     quieres
    1.78
    POSITIVE LOGITS
     (
    2.16
     ([
    1.90
     [
    1.79
    <sup>
    1.72
     $[
    1.63
     (~
    1.53
    [
    1.52
     (<
    1.51
    phen
    1.51
     sociocultural
    1.49
    Activations Density 0.467%

    No Known Activations