© 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. 9135
    Prev
    Next
    INDEX
    Explanations

    places and countries

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

    The neuron fires on numeric tokens—especially multi-digit numbers that denote counts or quantities.

    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
     químicas
    -2.17
    '
    -1.93
     engraçadas
    -1.77
    中心的
    -1.74
    ஂ
    -1.70
    ponenten
    -1.70
    --"
    -1.68
    
    -1.66
    ꗃ
    -1.59
     ubiquitous
    -1.57
    POSITIVE LOGITS
    కర్య
    1.84
    𞤪
    1.73
     the
    1.73
    嵛
    1.72
    我把
    1.70
     lesquels
    1.70
    𞤢
    1.63
     whom
    1.59
     are
    1.59
     Anſ
    1.59
    Activations Density 0.105%

    No Known Activations