© 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. 39753
    Prev
    Next
    INDEX
    Explanations

    fistula

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

    The neuron activates for medical terms related to fistulas and anatomical connections between organs or body parts.

    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
     he
    -1.55
     banyo
    -1.48
    只是一
    -1.46
    といけない
    -1.45
    拶
    -1.42
    舁
    -1.41
    ריים
    -1.40
    鹛
    -1.39
     gezondheid
    -1.38
    吖
    -1.37
    POSITIVE LOGITS
    焄
    1.54
    桃園
    1.49
    因为
    1.43
     BUT
    1.38
    訥
    1.38
     Verfügung
    1.35
    ञ
    1.34
     BTW
    1.33
    比如说
    1.33
     अलावा
    1.32
    Activations Density 0.068%

    No Known Activations