© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 106283
    Prev
    Next
    INDEX
    Explanations

    Mitochondrial, Systematic, DWI, Q

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

    non-English text and technical notations, particularly focusing on special characters and formatting in programming, math, and non-Latin scripts.

    oai_token-act-pair · claude-3-7-sonnet-20250219
    Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    lange
    -0.81
     Metab
    -0.72
    gesture
    -0.71
     Scr
    -0.71
     putern
    -0.70
     Alf
    -0.69
    择
    -0.68
     Vit
    -0.68
    quiry
    -0.67
    ၄
    -0.67
    POSITIVE LOGITS
    Após
    0.78
     SWIG
    0.77
    lac
    0.76
    싯
    0.76
     manuell
    0.74
     endowment
    0.72
    CITATION
    0.72
     Endowment
    0.72
    mips
    0.72
    Addiction
    0.71
    Activations Density 0.009%

    No Known Activations