© 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. 193341
    Prev
    Next
    INDEX
    Explanations

    running late, not attempt, we argue

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

    lists, topics, descriptions

    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
    出す
    0.52
    '
    0.46
    出した
    0.46
    ्ज
    0.44
     οι
    0.43
    出し
    0.42
    ダンス
    0.42
     पात
    0.41
    지
    0.41
    ajaan
    0.41
    POSITIVE LOGITS
     Bundes
    0.54
     deutsche
    0.50
     deutschen
    0.49
     फीफा
    0.49
     University
    0.47
     supersonic
    0.47
     Company
    0.46
     ইউনিভার্সিটি
    0.46
    筁
    0.46
     MongoDB
    0.46
    Activations Density 0.001%

    No Known Activations