© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 12994
    Prev
    Next
    INDEX
    Explanations

    point guards

    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
     Libertadores
    0.60
     Seller
    0.57
    헐
    0.57
    Vacancy
    0.55
    нять
    0.54
     renegoti
    0.54
     層
    0.54
     tenant
    0.53
     fath
    0.53
    佣
    0.53
    POSITIVE LOGITS
     guards
    0.84
     guard
    0.78
     point
    0.71
    point
    0.71
     shooting
    0.71
     guarding
    0.70
    guards
    0.68
    guard
    0.66
     Khr
    0.64
     SG
    0.64
    Activations Density 0.028%

    No Known Activations