© 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. 105732
    Prev
    Next
    INDEX
    Explanations

    growth metrics

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

    The neuron fires on numeric tokens—especially multi-digit figures and decimals (including percentage values)—i.e. it detects quantitative data 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
     vacunas
    -1.98
    鲼
    -1.96
     ellos
    -1.94
    尨
    -1.85
    ㆆ
    -1.81
    饜
    -1.75
    逦
    -1.73
     Infór
    -1.71
     попыта
    -1.69
    
    -1.69
    POSITIVE LOGITS
     on
    1.80
     in
    1.77
     between
    1.56
    另一
    1.52
     increase
    1.52
     In
    1.51
     .
    1.51
     for
    1.50
     $
    1.48
     at
    1.48
    Activations Density 0.019%

    No Known Activations