© 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. 8127
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and functions

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

    The neuron activates on numeric tokens (numbers, especially those with decimal points).

    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
     [
    -1.88
     или
    -1.80
     said
    -1.66
    </strong>
    -1.65
     -
    -1.56
    <blockquote>
    -1.55
     этих
    -1.52
    s
    -1.43
     –
    -1.42
     may
    -1.42
    POSITIVE LOGITS
     diny
    1.68
    跸
    1.67
     vinil
    1.63
     marah
    1.61
     sonda
    1.60
     laim
    1.55
     burbu
    1.53
     meras
    1.52
     taba
    1.52
     تنظ
    1.52
    Activations Density 0.035%

    No Known Activations