© 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. 22-GEMMASCOPE-RES-131K
    7. 73962
    Prev
    Next
    INDEX
    Explanations

    predicts association relationship

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

    The main thing this neuron does is detect numeric values (including 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_22/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
     If
    -1.16
     if
    -0.96
    APIView
    -0.93
    )=>{
    -0.91
    dataIndex
    -0.90
    pplung
    -0.90
     ".
    -0.89
    endwhile
    -0.88
    '.
    -0.87
    '].
    -0.86
    POSITIVE LOGITS
     Gemü
    1.19
     kabát
    1.17
     páns
    1.09
    怎样的
    1.05
     pomaga
    1.04
     zowel
    1.04
     luxus
    1.03
     univerz
    1.02
     konkrét
    1.02
     kré
    1.02
    Activations Density 0.120%

    No Known Activations