© 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-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 14163
    Prev
    Next
    INDEX
    Explanations

    sergeant

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_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
    Whilst
    1.09
     Whilst
    1.02
     &/
    0.91
     whilst
    0.91
     "...
    0.90
     हेतु
    0.88
     đc
    0.87
     ১ম
    0.85
     cca
    0.82
     "..
    0.82
    POSITIVE LOGITS
     ­
    1.06
    ,’’
    0.90
    .’’
    0.86
    ¬
    0.84
     [
    0.75
     [-
    0.72
     .”
    0.71
    ­
    0.70
     ¬
    0.70
     sergeant
    0.67
    Activations Density 0.032%

    No Known Activations