© 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. 10777
    Prev
    Next
    INDEX
    Explanations

    lists of items

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

    The neuron activates on numeric tokens (both integers and decimals).

    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
    There
    -2.44
     still
    -1.98
     In
    -1.95
     now
    -1.89
     There
    -1.88
     Some
    -1.83
    These
    -1.77
     During
    -1.73
    Some
    -1.67
     Many
    -1.65
    POSITIVE LOGITS
     how
    1.88
     aktivitet
    1.82
     butik
    1.78
     medier
    1.77
    
    1.75
     zubehör
    1.70
    がなく
    1.70
     défauts
    1.66
     nini
    1.64
     his
    1.61
    Activations Density 0.089%

    No Known Activations