© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 207934
    Prev
    Next
    INDEX
    Explanations

    development, gesch, nammen

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

    code execution, profit, abuse

    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
    Negative Logits
     親
    0.54
     flexion
    0.50
     cropping
    0.49
     剤
    0.49
     chỉ
    0.47
     ジ
    0.46
    のマ
    0.46
     gives
    0.46
    のス
    0.46
     đoạn
    0.45
    POSITIVE LOGITS
    esu
    0.47
    nahmen
    0.46
    مسه
    0.46
    asah
    0.45
    gesch
    0.44
    entwicklung
    0.43
    eqa
    0.43
    getragen
    0.43
    несла
    0.43
    뎅
    0.42
    Activations Density 0.002%

    No Known Activations