© 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. 48665
    Prev
    Next
    INDEX
    Explanations

    programming and functional queries

    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
     BBC
    0.47
    स्ताना
    0.47
     Heathrow
    0.46
    there
    0.46
    sez
    0.45
     ทอง
    0.45
    ครั้ง
    0.45
    麵
    0.43
     Međ
    0.43
     Television
    0.43
    POSITIVE LOGITS
    ה
    0.50
    ቾ
    0.48
    的基础
    0.46
     регу
    0.46
     exemplar
    0.46
    ه
    0.45
     affirms
    0.45
    a
    0.45
    Configure
    0.44
    Ự
    0.44
    Activations Density 0.000%

    No Known Activations