© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 176896
    Prev
    Next
    INDEX
    Explanations

    informative planning and insights

    np_acts-logits-general · gemini-2.5-flash-lite

    names and specific topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ச்செ
    0.47
     ਬਾ
    0.47
    ▥
    0.45
     ਇ
    0.45
    helpful
    0.44
    娱乐圈
    0.44
     ครับ
    0.44
    映画
    0.44
    グ
    0.44
     感じ
    0.44
    POSITIVE LOGITS
     Jamie
    0.54
     Bolt
    0.50
     Duncan
    0.48
     Back
    0.47
     Bolton
    0.46
     Bracken
    0.46
     More
    0.46
     while
    0.45
     Whisky
    0.45
     Nolan
    0.45
    Activations Density 0.000%

    No Known Activations