© 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. 73002
    Prev
    Next
    INDEX
    Explanations

    BCL-2 protein expression

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

    protein naming patterns like "BCL-2" and gene identifiers in scientific texts.

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

    This neuron fires on mentions of the BCL-2 gene/protein (uppercase letters plus “-2”).

    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
    </strong>
    -2.47
    鈰
    -1.73
    <td>
    -1.63
    quelize
    -1.63
    and
    -1.62
     ,‬
    -1.58
    檍
    -1.54
    感器
    -1.52
    it
    -1.48
    呖
    -1.46
    POSITIVE LOGITS
    哙
    1.49
     Würde
    1.44
    ሺ
    1.41
    禵
    1.40
    ebaran
    1.40
    荩
    1.37
     französ
    1.37
    している
    1.35
     häufigsten
    1.34
     implied
    1.33
    Activations Density 0.005%

    No Known Activations