© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78968
    Prev
    Next
    INDEX
    Explanations

    code arguments FROM

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

    The main thing this neuron does is detect numeric tokens—any standalone numbers or digit sequences 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
     uncertainty
    -0.72
     Applied
    -0.70
    σ
    -0.67
    applied
    -0.66
     uncertain
    -0.66
    strain
    -0.64
     getRequest
    -0.63
    astro
    -0.63
    締切
    -0.63
    ⭐⭐⭐⭐
    -0.61
    POSITIVE LOGITS
    ẵ
    0.72
    HIL
    0.70
     Decentral
    0.69
    heatmap
    0.68
    meau
    0.67
    wdriver
    0.66
    chrys
    0.66
    gmx
    0.66
    Ery
    0.66
    IDES
    0.66
    Activations Density 0.067%

    No Known Activations