© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 21863
    Prev
    Next
    INDEX
    Explanations

    numbers -1 and 1

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

    The neuron activates on numeric tokens (digits, integers, and decimals) embedded in the math 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
     also
    -1.27
     även
    -1.21
    🕺
    -1.12
    ❣️
    -1.12
    itize
    -1.11
    omato
    -1.10
    ↵
    -1.09
     ayrıca
    -1.09
    णी
    -1.09
    lllllll
    -1.09
    POSITIVE LOGITS
     wciąż
    1.23
     it
    1.23
     newfound
    1.22
    這些
    1.17
    comps
    1.14
    encre
    1.14
     its
    1.13
     protože
    1.11
     früheren
    1.11
    Estos
    1.10
    Activations Density 0.201%

    No Known Activations