© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 80044
    Prev
    Next
    INDEX
    Explanations

    explaining concepts or details

    np_acts-logits-general · gemini-2.5-flash-lite

    before a storm

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    ラ
    0.50
    কিন্তু
    0.47
    re
    0.47
     occasionally
    0.47
     posición
    0.46
     occasional
    0.46
    )(-
    0.46
    ヤ
    0.46
     których
    0.45
     exasper
    0.45
    POSITIVE LOGITS
     современ
    0.48
    انب
    0.46
     بند
    0.46
    程序员
    0.46
    Scape
    0.45
    孳
    0.45
    肓
    0.45
    సుకోవ
    0.45
    មូល
    0.45
     dissemination
    0.44
    Activations Density 0.000%

    No Known Activations