© 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-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 58704
    Prev
    Next
    INDEX
    Explanations

    Field Effect Transistor, Iron Gall Ink

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    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
     пропор
    0.42
    攥
    0.41
     ผ้า
    0.41
    PastPositions
    0.41
     विधेयक
    0.41
    𒌆
    0.40
    Игра
    0.39
    柰
    0.39
    प्लो
    0.37
     सुपरस्टार
    0.37
    POSITIVE LOGITS
     type
    0.45
     ar
    0.44
     desc
    0.41
     baseline
    0.40
     arct
    0.40
    ae
    0.39
     arche
    0.39
    ac
    0.38
    pak
    0.38
     closure
    0.38
    Activations Density 0.002%

    No Known Activations