© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 100675
    Prev
    Next
    INDEX
    Explanations

    Hep prefix

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

    The neuron activates for the medical term "Hepatitis" and related liver disease terminology.

    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
    “
    -3.73
    इटम
    -3.14
    '
    -2.89
    </u>
    -2.53
    
    -2.39
    —“
    -2.38
    谞
    -2.36
    ,“
    -2.34
     presidencia
    -2.28
    鸶
    -2.22
    POSITIVE LOGITS
    }$
    3.66
     biologique
    2.30
    鵟
    2.28
    샅
    2.27
    訕
    2.23
    蓠
    2.17
     ПРЕ
    2.14
     raccol
    2.13
    estões
    2.13
    and
    2.08
    Activations Density 0.017%

    No Known Activations