© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 64500
    Prev
    Next
    INDEX
    Explanations

    palmyra vitamin[ package

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

    The neuron activates on numeric literal tokens (integer or decimal numbers) in code and text.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    AFFIRMED
    -1.01
    gpu
    -0.95
     double
    -0.94
    ıld
    -0.93
    мите
    -0.90
    董事
    -0.90
     viewWillAppear
    -0.90
    Poloha
    -0.89
     unconventional
    -0.86
    менно
    -0.85
    POSITIVE LOGITS
     gradually
    0.95
     values
    0.92
    veta
    0.89
     kwiet
    0.87
     cajas
    0.87
     belangrijk
    0.85
     jakim
    0.85
     vær
    0.83
    aptation
    0.83
     bazı
    0.83
    Activations Density 0.023%

    No Known Activations