© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 3891
    Prev
    Next
    INDEX
    Explanations

    leukemia, StatusCode, Jain

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

    The neuron detects mentions of leukemia and medical terminology related to blood cancers.

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

    This neuron activates strongly on specific named-entity tokens, especially proper nouns for religions (e.g. “Jain,” “Jainism”) and diseases (e.g. “leukemia”).

    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
     }
    -2.39
     \
    -2.33
     -
    -2.33
    .
    -2.28
     apenas
    -2.28
    ⧠
    -2.27
     него
    -2.22
    那就
    -2.20
    聍
    -2.03
    铪
    -2.03
    POSITIVE LOGITS
    the
    2.67
     باستخدام
    2.64
    سبة
    2.56
    these
    2.23
    ить
    2.17
     viera
    2.16
    您
    2.14
    躥
    2.09
    Many
    2.08
    　『
    2.06
    Activations Density 0.003%

    No Known Activations