© 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-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 43398
    Prev
    Next
    INDEX
    Explanations

    reorganize, redefine, allocate, redistribute

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    and
    1.73
    up
    1.70
    箋
    1.68
    Uit
    1.62
    Ns
    1.54
    Ihr
    1.52
    fia
    1.49
    Nm
    1.48
    P
    1.48
    ۲
    1.48
    POSITIVE LOGITS
    ка
    2.38
    де
    1.95
    и
    1.81
    т
    1.77
    дан
    1.71
    د
    1.66
    он
    1.60
    ᄍ
    1.59
    ون
    1.52
    ра
    1.49
    Activations Density 0.058%

    No Known Activations