© 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. 13868
    Prev
    Next
    INDEX
    Explanations

    org

    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
     Gladiator
    0.61
    ʕ
    0.59
    颛
    0.57
    藪
    0.55
    ходу
    0.55
     Gloucester
    0.55
     fieldContext
    0.55
     Rooster
    0.54
    舐
    0.53
    Venus
    0.52
    POSITIVE LOGITS
    rg
    1.84
    urg
    1.77
    arg
    1.73
    erg
    1.71
    berg
    1.65
    burg
    1.65
     burg
    1.64
    Burg
    1.64
    рг
    1.63
     Burg
    1.59
    Activations Density 0.094%

    No Known Activations