© 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. 100283
    Prev
    Next
    INDEX
    Explanations

    RAC1/NADPH oxidase in nerve growth factor induction

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

    This neuron detects numbers and numeric identifiers in text, including chemical formulas, medication names, and specific disease/disorder classifications.

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

    The neuron strongly activates on individual capitalized terms, acronyms, and alphanumeric tokens (proper names, technical abbreviations, model numbers, etc.).

    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
    4
    -1.58
    2
    -1.54
     empêcher
    -1.52
    </h3>
    -1.48
     ayur
    -1.45
    er
    -1.43
    larg
    -1.42
    ه
    -1.42
    ayage
    -1.42
    ,
    -1.41
    POSITIVE LOGITS
     verdure
    1.52
     peculi
    1.47
    corrhi
    1.46
    梣
    1.44
     tramont
    1.44
     barran
    1.44
     churras
    1.43
     veter
    1.43
     plata
    1.41
     tuta
    1.41
    Activations Density 0.055%

    No Known Activations