© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 111925
    Prev
    Next
    INDEX
    Explanations

    expressing possibility or doubt

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

    The neuron responds to numerical tokens or numeric expressions (e.g. numbers and quantities) in the text.

    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
    任何
    -1.45
     any
    -1.28
     or
    -1.20
    حه
    -1.19
     kahit
    -1.15
    н
    -1.15
     crudo
    -1.13
    he
    -1.13
    p
    -1.10
    他的
    -1.09
    POSITIVE LOGITS
    ྄
    1.54
    杳
    1.44
     Nós
    1.38
     dnes
    1.37
    ylation
    1.36
    姗
    1.34
    fillment
    1.31
    もありました
    1.29
    िक
    1.28
    枷
    1.28
    Activations Density 0.011%

    No Known Activations