© 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. 400
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ఎం
    1.15
    젝트
    1.09
    ỉ
    1.03
    ocar
    1.01
    zA
    0.97
    js
    0.95
    iska
    0.95
    [
    0.95
    ئات
    0.94
    aiset
    0.92
    POSITIVE LOGITS
     attentively
    1.93
     intently
    1.84
    andfeel
    1.76
    <unused989>
    1.64
    াভাব
    1.58
    <unused1706>
    1.57
     nervously
    1.55
    <unused946>
    1.51
     favorably
    1.49
    <unused718>
    1.49
    Activations Density 1.912%

    No Known Activations