© 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. 59710
    Prev
    Next
    INDEX
    Explanations

    indices in mathematical formulas

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

    The neuron detects numeric values (integers and decimals) in mathematical expressions.

    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
     to
    -2.06
     complete
    -1.62
     that
    -1.52
     による
    -1.49
    いいのか
    -1.48
    ,
    -1.48
     a
    -1.46
     due
    -1.45
     paš
    -1.43
     inmiddels
    -1.43
    POSITIVE LOGITS
    ativement
    1.55
    ")
    1.53
     estés
    1.46
    ","
    1.43
     lisse
    1.41
     éduc
    1.41
    \
    1.41
    」、「
    1.36
     ktorá
    1.35
     LOTS
    1.35
    Activations Density 0.014%

    No Known Activations