© 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-65K
    7. 47524
    Prev
    Next
    INDEX
    Explanations

    introductory courses or guides

    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_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ov
    0.40
    pause
    0.40
    fix
    0.39
    ine
    0.38
     CAT
    0.38
    …
    0.38
    +
    0.38
    ot
    0.37
    cat
    0.37
    stack
    0.37
    POSITIVE LOGITS
     theorist
    0.43
     curriculum
    0.42
     tarixində
    0.41
    焓
    0.41
    デル
    0.41
    섹
    0.41
     splic
    0.40
    工程师
    0.40
    很好
    0.40
     repression
    0.40
    Activations Density 0.007%

    No Known Activations