© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 145341
    Prev
    Next
    INDEX
    Explanations

    directory names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     використову
    0.64
     usados
    0.60
     sodio
    0.59
    piry
    0.56
     ନ
    0.55
     мають
    0.55
    人用
    0.54
     два
    0.53
     usado
    0.53
     χρησιμοποι
    0.53
    POSITIVE LOGITS
    V
    0.75
    K
    0.61
    J
    0.59
    F
    0.54
    W
    0.53
    Ō
    0.53
    Vol
    0.52
    {'
    0.52
    Qatar
    0.52
    Saudi
    0.51
    Activations Density 0.000%

    No Known Activations