© 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. 22-GEMMASCOPE-RES-131K
    7. 73427
    Prev
    Next
    INDEX
    Explanations

    mathematical notation formatting

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

    The neuron activates on numeric tokens (digits or numbers) appearing in equations or 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_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
    があり
    -1.63
    栒
    -1.38
     constructeur
    -1.38
     minimale
    -1.37
     accompagner
    -1.35
     siè
    -1.35
    錾
    -1.33
     registre
    -1.31
     perles
    -1.31
     alfo
    -1.31
    POSITIVE LOGITS
     {
    1.64
    n
    1.56
    1
    1.48
    </strong>
    1.48
    O
    1.41
    3
    1.41
     ("
    1.35
    2
    1.34
    e
    1.33
    5
    1.32
    Activations Density 0.002%

    No Known Activations