© 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. 129726
    Prev
    Next
    INDEX
    Explanations

    LaTeX math formatting

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

    The neuron detects standalone numeric tokens (integers or 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_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
     would
    -1.70
     =
    -1.70
     那
    -1.59
    );
    -1.50
    enzi
    -1.46
    M
    -1.45
    之以
    -1.41
    ;.
    -1.40
     oiseaux
    -1.36
    ,.
    -1.34
    POSITIVE LOGITS
    们的
    1.48
    桄
    1.47
    1.41
    蹰
    1.40
    Klik
    1.39
    してくれた
    1.39
    
    1.38
     если
    1.38
    lised
    1.37
    Externé
    1.36
    Activations Density 0.002%

    No Known Activations