© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 9678
    Prev
    Next
    INDEX
    Explanations

    numbers in code

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

    The neuron activates on numeric literal tokens, i.e. when raw numbers (integers or decimals) appear.

    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
     of
    -1.74
    ing
    -1.64
     our
    -1.47
     ネタバレ
    -1.46
    maybe
    -1.38
     about
    -1.38
    #%%
    -1.35
    说过
    -1.34
     别墅
    -1.33
    年は
    -1.32
    POSITIVE LOGITS
    RITION
    1.74
    rogène
    1.71
     incluindo
    1.66
    atchewan
    1.62
    UNITIES
    1.61
    škin
    1.60
    renden
    1.59
    ideae
    1.59
    ificado
    1.59
    cés
    1.58
    Activations Density 0.066%

    No Known Activations