© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 26310
    Prev
    Next
    INDEX
    Explanations

    body parts and medical conditions

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

    body parts and anatomical terms.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     for
    -1.17
    b
    -1.11
     fortfarande
    -1.02
     kelahiran
    -1.02
    terer
    -1.00
    c
    -1.00
    i
    -1.00
     niitä
    -0.97
    сила
    -0.96
    s
    -0.96
    POSITIVE LOGITS
     Dijo
    1.35
    szt
    1.23
     entregas
    1.17
     Estaba
    1.16
    延伸閱讀
    1.16
     윤
    1.09
     entire
    1.09
     llevaba
    1.07
     Lleg
    1.06
     vivía
    1.06
    Activations Density 0.075%

    No Known Activations