© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 69933
    Prev
    Next
    INDEX
    Explanations

    numerical identifiers

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

    The neuron fires on numeric tokens—especially numbers (including those with decimal points).

    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
     apprehensive
    -2.23
     και
    -2.13
     dari
    -2.11
    észetes
    -2.11
    ࿙
    -2.08
    utiva
    -2.08
    </h4>
    -2.03
    汌
    -2.02
    
    -1.97
    ⾦
    -1.95
    POSITIVE LOGITS
    il
    2.27
    ‘
    2.19
    '
    2.16
    ↵
    2.14
     dasarnya
    2.05
    ↵↵↵
    2.03
     first
    1.99
    D
    1.95
    ↵↵
    1.94
    ar
    1.94
    Activations Density 0.119%

    No Known Activations