© 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. 13089
    Prev
    Next
    INDEX
    Explanations

    medicine

    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
    芒
    0.50
    orschungs
    0.48
    上が
    0.48
    養成
    0.48
     ಹೊಂದಿ
    0.47
     Manohar
    0.47
    unki
    0.47
    槙
    0.46
    ικού
    0.46
     dioc
    0.46
    POSITIVE LOGITS
     medicine
    4.22
     Medicine
    4.19
    Medicine
    4.06
    medicine
    3.91
     MEDIC
    3.88
    Med
    3.77
     Med
    3.75
    MED
    3.67
     med
    3.63
     MED
    3.61
    Activations Density 0.127%

    No Known Activations