© 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. 34-GEMMASCOPE-RES-131K
    7. 90565
    Prev
    Next
    INDEX
    Explanations

    human genome and genetics

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

    gene or protein identifiers in scientific or technical text.

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

    This neuron detects mentions of genes along with their chromosomal mapping or numerical identifiers.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     salg
    -0.74
     inland
    -0.74
     Inland
    -0.74
    jani
    -0.74
    firmasi
    -0.73
     foreigners
    -0.72
     konkrete
    -0.71
    Witch
    -0.71
    плуата
    -0.69
    merking
    -0.69
    POSITIVE LOGITS
     prefier
    0.97
    PubMed
    0.97
    готов
    0.96
    HUMAN
    0.95
    izaron
    0.90
    -->
    0.88
    give
    0.88
    ged
    0.85
    have
    0.85
    ‎
    0.85
    Activations Density 0.118%

    No Known Activations