© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 21024
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and questions

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

    The neuron activates on numeric values (digits and decimal numbers) 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
    typically
    -1.64
     drei
    -1.53
    珦
    -1.49
    🚆
    -1.44
     acoged
    -1.42
     rö
    -1.41
    doir
    -1.40
     ainsi
    -1.40
    marzo
    -1.40
     inklusive
    -1.39
    POSITIVE LOGITS
     when
    1.80
     distru
    1.60
     merito
    1.55
     rotund
    1.54
     because
    1.51
     solas
    1.49
     after
    1.48
     felici
    1.45
     does
    1.40
     didn
    1.39
    Activations Density 0.008%

    No Known Activations