© 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. 31-GEMMASCOPE-2-RES-262K
    7. 80092
    Prev
    Next
    INDEX
    Explanations

    custom, initialization, resource types

    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_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     కావ
    0.48
     дверь
    0.46
     зави
    0.45
     बुजुर्ग
    0.45
    roomId
    0.45
     Закон
    0.45
     ব্যাবস্থা
    0.45
     冖
    0.44
     effectual
    0.42
     orphans
    0.42
    POSITIVE LOGITS
    <h1>
    0.56
    महाराष्ट
    0.43
    이고
    0.40
     nautical
    0.40
     high
    0.40
     Nautical
    0.40
     your
    0.40
     springs
    0.39
     conferences
    0.39
     deep
    0.38
    Activations Density 0.005%

    No Known Activations