© 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. 210342
    Prev
    Next
    INDEX
    Explanations

    hygiene standards, rated entity, teeth whitening, hour

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

    expensive training

    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
     highScore
    0.55
     从
    0.50
     这个
    0.48
    编码
    0.47
     comunicação
    0.47
    运转
    0.47
     entwick
    0.46
     automó
    0.46
     环境
    0.46
    imgInit
    0.46
    POSITIVE LOGITS
    ED
    0.56
    オ
    0.52
    a
    0.48
     offerings
    0.48
    aus
    0.48
    ed
    0.47
    us
    0.46
    2
    0.46
    vu
    0.46
     displaying
    0.46
    Activations Density 0.004%

    No Known Activations