© 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. 2581
    Prev
    Next
    INDEX
    Explanations

    non, multi, semi prefixes

    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
     D
    1.78
     a
    1.77
     at
    1.73
     b
    1.67
     Of
    1.66
     in
    1.60
     iba
    1.60
     Total
    1.59
     [
    1.59
     als
    1.58
    POSITIVE LOGITS
    lipidemia
    2.81
    ethnic
    2.65
    acly
    2.63
    vehicle
    2.61
    huile
    2.55
    wheeled
    2.52
    operative
    2.51
    industrial
    2.49
    peration
    2.47
    ordi
    2.43
    Activations Density 0.551%

    No Known Activations