© 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. 10-GEMMASCOPE-RES-131K
    7. 127912
    Prev
    Next
    INDEX
    Explanations

    gastroenterology and antero compounds

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

    medical and anatomical terminology, particularly relating to body parts and medical specialties.

    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_10/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
    '
    -3.39
    沕
    -3.05
    舠
    -2.80
    屺
    -2.72
    bluza
    -2.66
     winkel
    -2.66
    Ꮀ
    -2.61
    猡
    -2.56
    ⃙
    -2.56
    城的
    -2.56
    POSITIVE LOGITS
    I
    2.64
    ing
    2.63
    那個
    2.61
    ︐
    2.52
    6
    2.50
    if
    2.44
    8
    2.42
    5
    2.38
    4
    2.38
     tetapi
    2.34
    Activations Density 0.029%

    No Known Activations