© 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. 59596
    Prev
    Next
    INDEX
    Explanations

    lower respiratory/urinary/extremity/plasma

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

    The neuron detects the word "lower" in medical and scientific contexts, particularly related to health measures, medical conditions, and treatment effects.

    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
     Herbs
    -1.70
    姽
    -1.69
    vader
    -1.69
    圌
    -1.65
     utiliser
    -1.63
    odorant
    -1.61
     chè
    -1.59
    chantment
    -1.58
     preval
    -1.57
    力和
    -1.56
    POSITIVE LOGITS
    }$.
    2.28
    ↵↵
    2.14
     on
    1.93
     can
    1.78
     any
    1.74
    At
    1.71
    .”
    1.70
     possibly
    1.68
    On
    1.68
     at
    1.65
    Activations Density 0.003%

    No Known Activations