© 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. 41-GEMMASCOPE-2-RES-262K
    7. 21368
    Prev
    Next
    INDEX
    Explanations

    excerpt or extract

    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_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    လိုက်
    0.36
    راتيج
    0.36
     girlfriend
    0.35
     విజ
    0.35
    юз
    0.35
     reinstatement
    0.34
    erler
    0.34
    蝟
    0.34
     parked
    0.33
    uyan
    0.33
    POSITIVE LOGITS
     excerpt
    2.61
     excerpts
    2.52
    Excerpt
    2.36
    excerpt
    2.28
     extracts
    2.23
     extract
    2.16
     Extracts
    2.06
    Extract
    2.00
     Extract
    1.98
    extract
    1.98
    Activations Density 0.001%

    No Known Activations