© 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. 57917
    Prev
    Next
    INDEX
    Explanations

    Prague, Czech Republic

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

    The neuron is triggered by numeric tokens—especially sequences of digits like grant numbers, dates, distances, and other numerical data.

    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
    __;
    -0.85
    Ȼ
    -0.85
    extrême
    -0.82
     turmoil
    -0.79
     outfit
    -0.79
     裙
    -0.79
     bilhões
    -0.77
     charity
    -0.75
    CommandText
    -0.75
    mäßig
    -0.74
    POSITIVE LOGITS
     Praha
    0.96
    čení
    0.81
    UCL
    0.74
     Bohemian
    0.74
     find
    0.72
    母
    0.72
     Jeune
    0.70
    renderer
    0.70
    šas
    0.68
     znamen
    0.68
    Activations Density 0.011%

    No Known Activations