© 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. 62571
    Prev
    Next
    INDEX
    Explanations

    primitive neuro, types, hemato, or

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

    words related to programming primitives and primitive data types.

    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
     выполнять
    -0.91
     ere
    -0.83
    帮我
    -0.82
    まち
    -0.82
    activ
    -0.82
     adven
    -0.78
    lam
    -0.77
     CREATED
    -0.77
    随便
    -0.77
     ...
    -0.77
    POSITIVE LOGITS
    primitive
    1.04
     Importantly
    0.97
    istungen
    0.97
    міністра
    0.93
     навер
    0.93
     स्थित
    0.91
     ?>
    0.90
    靼
    0.90
    FECT
    0.90
    However
    0.89
    Activations Density 0.015%

    No Known Activations