© 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. 22-GEMMASCOPE-2-RES-16K
    7. 10591
    Prev
    Next
    INDEX
    Explanations

    overmix

    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_22_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
    keye
    0.76
    뵌
    0.70
    ographie
    0.68
    éristique
    0.68
    клары
    0.65
    utenant
    0.64
     şeyler
    0.64
     matern
    0.64
    ája
    0.64
    vieve
    0.63
    POSITIVE LOGITS
    Hamilton
    0.71
    $\
    0.69
    compet
    0.68
    rainbow
    0.66
    problem
    0.64
     Новосибир
    0.64
    Ronald
    0.63
    Elvis
    0.62
    荆
    0.62
    Bruno
    0.61
    Activations Density 0.140%

    No Known Activations