© 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. 30909
    Prev
    Next
    INDEX
    Explanations

    army march

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

    The neuron primarily detects 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
    spod
    -0.82
    ZQ
    -0.79
    uffy
    -0.79
    emporio
    -0.79
    immobili
    -0.78
    kawasaki
    -0.74
    onore
    -0.73
    braz
    -0.73
    empor
    -0.71
    ensacola
    -0.71
    POSITIVE LOGITS
    รุ่น
    0.91
     transfection
    0.90
     combustion
    0.88
     монта
    0.85
     pollination
    0.82
     gül
    0.81
    medik
    0.80
    kampf
    0.77
     cuddle
    0.77
     passende
    0.77
    Activations Density 0.064%

    No Known Activations