© 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. 13841
    Prev
    Next
    INDEX
    Explanations

    redo/update/repeat

    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
    തമായ
    0.52
     clonal
    0.50
    ラの
    0.49
    leveland
    0.49
    ленные
    0.49
    ո
    0.49
    Facilities
    0.48
    ौ
    0.48
    zett
    0.48
    Ｏ
    0.48
    POSITIVE LOGITS
    itext
    0.67
    াপ্র
    0.61
    yside
    0.61
    ilab
    0.60
    iloc
    0.57
     शुभ
    0.57
    圜
    0.56
    ndef
    0.55
    iflower
    0.54
    iblock
    0.54
    Activations Density 0.110%

    No Known Activations