© 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. 67921
    Prev
    Next
    INDEX
    Explanations

    hemoglobin and related conditions

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

    terms related to hemoglobin and blood disorders, especially thalassemia and hemoglobinopathies.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron responds to occurrences of hemoglobin (and closely related terms like globin, Hb, thalassemia, anemia, etc.), effectively detecting mentions of hemoglobin or hemoglobin‐related disorders.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    錞
    -2.58
    笤
    -2.39
    ⸫
    -2.36
    ཋ
    -2.30
     eşofman
    -2.27
    过多
    -2.25
    闼
    -2.25
    咘
    -2.20
    imize
    -2.16
    呿
    -2.16
    POSITIVE LOGITS
    ↵
    2.53
     trivi
    2.17
    ),
    2.03
    Ꭳ
    2.02
    <h2>
    1.98
    </h2>
    1.94
    ]
    1.92
    "
    1.91
     isnt
    1.87
    the
    1.86
    Activations Density 0.025%

    No Known Activations