© 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. 34-GEMMASCOPE-RES-131K
    7. 116176
    Prev
    Next
    INDEX
    Explanations

    filtering, diffusion, frequency

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

    The main thing this neuron does is find 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
     swing
    -0.71
    %)$
    -0.69
    是我的
    -0.67
    swipe
    -0.67
    enzuela
    -0.66
    がて
    -0.66
     Woodford
    -0.66
     Hamburger
    -0.66
    zeera
    -0.65
    ร้อน
    -0.65
    POSITIVE LOGITS
     Witkin
    0.85
    Stopping
    0.80
    ackerel
    0.77
     Stopping
    0.75
     Computed
    0.75
     النفس
    0.73
    NVIDIA
    0.73
    muli
    0.71
     vilá
    0.71
    urous
    0.71
    Activations Density 0.026%

    No Known Activations