© 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. 221293
    Prev
    Next
    INDEX
    Explanations

    places from

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

    work that meets requirements

    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
     niente
    0.47
    邪魔
    0.47
    ロゴ
    0.46
     Khim
    0.46
     ਨ
    0.46
    ώντας
    0.46
    ρίας
    0.45
    ievers
    0.45
     maniak
    0.45
     hing
    0.45
    POSITIVE LOGITS
    އް
    0.45
     inductively
    0.42
    병원
    0.42
    Co
    0.41
    बी
    0.40
    ستخدم
    0.40
     Astronomy
    0.39
    বা
    0.39
    预计
    0.38
    圆
    0.38
    Activations Density 0.001%

    No Known Activations