© 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. 9368
    Prev
    Next
    INDEX
    Explanations

    get something

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

    This neuron detects numerical tokens, especially decimal numbers (e.g. “123.5,” “54.75,” “27.875”).

    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
    g
    -2.00
    you
    -1.86
    on
    -1.79
    czny
    -1.79
    𓋼
    -1.77
    </h1>
    -1.73
     februari
    -1.58
     "")
    -1.55
    ！”
    -1.53
    te
    -1.51
    POSITIVE LOGITS
     legions
    1.71
    aians
    1.57
     ajuda
    1.48
     enfoque
    1.45
    urches
    1.43
    ipen
    1.42
     sufficient
    1.41
     ‘’
    1.38
     estatu
    1.38
     оказался
    1.38
    Activations Density 0.063%

    No Known Activations