© 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. 13-GEMMASCOPE-2-RES-65K
    7. 1723
    Prev
    Next
    INDEX
    Explanations

    can’t be determined

    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_65k_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
    -
    0.66
     [
    0.64
    sic
    0.62
     “
    0.60
    ↵
    0.60
     plus
    0.59
     "
    0.59
     (
    0.56
     even
    0.54
    —
    0.53
    POSITIVE LOGITS
    <unused1382>
    1.56
    <unused1461>
    1.55
    <unused1531>
    1.55
    <unused1499>
    1.53
    <unused1526>
    1.52
    <unused1373>
    1.52
    <unused1462>
    1.50
    <unused1429>
    1.50
    <unused1528>
    1.50
    <unused1287>
    1.50
    Activations Density 1.084%

    No Known Activations