© 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. 22-GEMMASCOPE-RES-131K
    7. 129449
    Prev
    Next
    INDEX
    Explanations

    This neuron specializes in spotting technical genetic‐and‐genomic terminology, especially gene names (e.g. ApoE) and variant/polymorphism identifiers (e.g. rs numbers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    biomedical terms and abbreviations

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

    scientific and chemical terms and formulas in academic research papers.

    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_22/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
    ჻
    -1.81
     имму
    -1.60
    Spesifikasi
    -1.59
     ſer
    -1.56
     meski
    -1.56
     trouvent
    -1.56
     chúc
    -1.49
    
    -1.48
     internetu
    -1.48
     niedersachsen
    -1.47
    POSITIVE LOGITS
     had
    1.70
     one
    1.64
     on
    1.56
     in
    1.52
     having
    1.46
     at
    1.45
     it
    1.45
     as
    1.44
     which
    1.43
     (
    1.42
    Activations Density 0.347%

    No Known Activations