© 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. 7483
    Prev
    Next
    INDEX
    Explanations

    skin or symptoms

    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
     notoriously
    2.11
     strikingly
    2.04
    <unused2121>
    1.90
    <unused170>
    1.89
    <unused2172>
    1.89
     extraordinarily
    1.87
     decidedly
    1.85
    <unused969>
    1.85
    presumably
    1.84
     remarkably
    1.84
    POSITIVE LOGITS
    (
    1.70
     없음
    1.69
     ไม่
    1.68
    （
    1.64
    及
    1.63
     全
    1.62
    =>
    1.58
    =
    1.57
    +
    1.57
     И
    1.56
    Activations Density 0.150%

    No Known Activations