© 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. 99458
    Prev
    Next
    INDEX
    Explanations

    anemia

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

    This neuron detects medical terms related to anemia, with highest activations for direct mentions of "anemia" in medical contexts.

    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
    苙
    -2.00
    ꯳
    -1.91
    羕
    -1.91
     praktischen
    -1.89
     Our
    -1.88
    吵架
    -1.88
    のいい
    -1.84
    錞
    -1.84
    今も
    -1.84
     ก็
    -1.82
    POSITIVE LOGITS
    }$
    3.17
    },
    2.06
    </b>
    2.03
    ۵
    2.03
    ৫
    1.91
     pentru
    1.90
     {
    1.90
    </h1>
    1.89
    ),
    1.80
    ｔ
    1.79
    Activations Density 0.034%

    No Known Activations