© 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. 3136
    Prev
    Next
    INDEX
    Explanations

    code comments and annotations

    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
     fastest
    0.42
    yx
    0.41
     safest
    0.39
     skills
    0.38
     quickest
    0.38
     loyalty
    0.37
     freighter
    0.36
     பிடித்த
    0.36
    fraud
    0.36
    免
    0.36
    POSITIVE LOGITS
    Throughout
    0.92
     Throughout
    0.90
     throughout
    0.84
    注释
    0.84
     komentar
    0.83
     comments
    0.82
     комментария
    0.82
     annotations
    0.80
     commentaires
    0.80
     comentários
    0.78
    Activations Density 0.019%

    No Known Activations