© 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. 235682
    Prev
    Next
    INDEX
    Explanations

    receiving spa

    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
    あ
    0.54
    怎么
    0.52
    あなたの
    0.48
    使用
    0.47
    你的
    0.47
    あなた
    0.47
    あなたが
    0.47
    你在
    0.46
    頑
    0.46
    يع
    0.46
    POSITIVE LOGITS
    conductor
    0.50
    ds
    0.48
    bler
    0.47
    .''
    0.47
    ba
    0.47
    ''.
    0.47
     cevap
    0.46
    ji
    0.45
    dz
    0.44
    facts
    0.44
    Activations Density 0.001%

    No Known Activations