© 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. 2610
    Prev
    Next
    INDEX
    Explanations

    labels and definitions

    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
    eterminate
    1.59
    enderal
    1.58
    ⺝
    1.58
    ρων
    1.57
    頩
    1.56
    =","><
    1.55
    subplot
    1.55
    睉
    1.54
    myCollision
    1.54
    轫
    1.54
    POSITIVE LOGITS
     led
    1.48
    iferous
    1.39
    /
    1.37
     as
    1.33
     should
    1.32
     out
    1.31
     to
    1.31
     suitably
    1.26
     aus
    1.26
    حي
    1.24
    Activations Density 0.000%

    No Known Activations