© 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. 45013
    Prev
    Next
    INDEX
    Explanations

    vascular medical terms

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

    The neuron detects the word "vascular" and related terms about blood vessels or the circulatory system.

    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
    麈
    -3.17
     ſou
    -2.56
     occuper
    -2.52
     stanga
    -2.52
    埽
    -2.47
    屺
    -2.45
    縺
    -2.44
    鼕
    -2.42
    ambiance
    -2.41
     animaux
    -2.39
    POSITIVE LOGITS
    i
    4.09
    b
    3.81
    c
    3.58
    =
    3.11
    -
    2.94
    f
    2.84
     &
    2.83
    --
    2.83
    ch
    2.80
    ;
    2.70
    Activations Density 0.021%

    No Known Activations