© 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. 39326
    Prev
    Next
    INDEX
    Explanations

    a followed by a descriptive word

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

    The neuron fires on numeric tokens, i.e. measurements or quantities (integers and decimals) in the text.

    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
     problems
    -1.95
     various
    -1.84
     different
    -1.81
     their
    -1.80
     changes
    -1.78
    ؽ
    -1.75
     because
    -1.70
     difficulties
    -1.68
     Numerous
    -1.67
     numerous
    -1.65
    POSITIVE LOGITS
     incredibly
    1.60
    </sub>
    1.58
    didn
    1.57
     essas
    1.52
     manières
    1.50
    Its
    1.48
     lui
    1.48
     “
    1.48
     dessa
    1.48
     strikingly
    1.47
    Activations Density 0.177%

    No Known Activations