© 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. 34-GEMMASCOPE-RES-131K
    7. 76240
    Prev
    Next
    INDEX
    Explanations

    numbers and versions

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

    The main thing this neuron does is detect numeric tokens (numbers) 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_34/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
    警惕
    -0.77
    ActionBar
    -0.67
    Sheila
    -0.65
    장
    -0.65
    ชาติ
    -0.65
     uninsured
    -0.65
     Sheila
    -0.64
    heets
    -0.63
    Millis
    -0.62
    شتی
    -0.62
    POSITIVE LOGITS
    섭
    0.71
    cooking
    0.69
    Poss
    0.66
     اث
    0.66
     sept
    0.65
     домов
    0.62
    Parallel
    0.62
     dug
    0.62
    を与える
    0.61
    capt
    0.61
    Activations Density 0.081%

    No Known Activations