© 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. 98931
    Prev
    Next
    INDEX
    Explanations

    deep exploration, Richard Lorenc, Foreign exchange

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

    The neuron is triggered primarily by numeric tokens or numeric literals (digits, version numbers, percentages, etc.).

    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
    බ
    -0.76
     countless
    -0.73
     primarily
    -0.70
     prz
    -0.68
     relatively
    -0.68
     three
    -0.67
     mainly
    -0.66
     four
    -0.66
     not
    -0.65
     data
    -0.65
    POSITIVE LOGITS
     Swa
    1.09
    ęć
    0.96
     Dinas
    0.92
    amesh
    0.91
     регуляр
    0.90
    Boron
    0.88
     aneur
    0.86
    ceno
    0.85
     árvores
    0.85
    tableau
    0.84
    Activations Density 0.006%

    No Known Activations