© 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. 15387
    Prev
    Next
    INDEX
    Explanations

    command line

    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
     Vaccine
    0.58
    育
    0.57
    ھار
    0.55
    ViewGroup
    0.54
     ViewGroup
    0.54
     Cáceres
    0.53
    UVW
    0.52
     coag
    0.52
    冲突
    0.52
    鯢
    0.52
    POSITIVE LOGITS
     terminal
    2.56
    Terminal
    2.41
    terminal
    2.39
     Terminal
    2.39
    命令行
    2.31
     टर्मिनल
    2.25
     CLI
    2.19
    コマンド
    2.17
    终端
    2.13
     terminals
    2.11
    Activations Density 0.079%

    No Known Activations