© 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. 10-GEMMASCOPE-RES-131K
    7. 68650
    Prev
    Next
    INDEX
    Explanations

    agronomic husbandry, Senegal, -manship

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

    words related to agriculture, crop science, and country names (particularly Senegal).

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    瞜
    -2.19
     включая
    -2.17
    辚
    -2.09
     ของ
    -2.02
    我就
    -2.00
    もちろん
    -1.98
    鬭
    -1.95
    啪
    -1.92
    ʽ
    -1.91
    鯡
    -1.91
    POSITIVE LOGITS
    2.81
    夲
    2.67
    橚
    2.59
    鸶
    2.55
    靣
    2.34
    偁
    2.33
    '));

    2.17
    manship
    2.17
    ܖ
    2.17
    ’.”
    2.09
    Activations Density 0.002%
    No Known Activations