© 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. 12670
    Prev
    Next
    INDEX
    Explanations

    competencies, skills

    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
     Kohn
    0.55
     DISCLAIM
    0.55
    波動方程式
    0.55
    tidy
    0.54
    żeń
    0.54
     overruled
    0.54
    嬌
    0.54
     summ
    0.52
    ুরী
    0.52
     لمح
    0.52
    POSITIVE LOGITS
    勺
    0.61
     Intersection
    0.57
    ूस
    0.57
    UCE
    0.57
     निष्
    0.56
    OTS
    0.55
    argo
    0.55
     एसपी
    0.55
    xC
    0.55
    USED
    0.54
    Activations Density 0.000%

    No Known Activations