© 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. 40-GEMMASCOPE-2-RES-262K
    7. 130157
    Prev
    Next
    INDEX
    Explanations

    demonstrate the capability

    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_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    1
    0.63
    다
    0.57
    Paw
    0.52
    Describe
    0.50
    Dimension
    0.47
    I
    0.47
    ID
    0.47
    و
    0.46
    function
    0.46
    だ
    0.46
    POSITIVE LOGITS
    ності
    0.58
    شتی
    0.51
    тыми
    0.50
    owanych
    0.49
    ڦ
    0.49
     acumen
    0.49
    ுமி
    0.48
    ٹس
    0.48
     Theorems
    0.47
    anlı
    0.46
    Activations Density 0.017%

    No Known Activations