© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 81134
    Prev
    Next
    INDEX
    Explanations

    font settings and spacing

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

    The neuron selectively fires on numeric tokens (standalone digits or numbers, including those with punctuation/decimal formatting).

    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
    ,‎
    -0.77
    conhe
    -0.75
     głowy
    -0.73
    卧室
    -0.73
     ого
    -0.71
    िए
    -0.71
    verton
    -0.71
    odendron
    -0.70
    ž
    -0.69
    iga
    -0.69
    POSITIVE LOGITS
     Spacing
    1.16
     spacing
    1.09
     Times
    1.03
     margins
    1.01
     pica
    0.99
    spacing
    0.98
     unjustified
    0.95
     font
    0.90
     space
    0.90
    Spacing
    0.86
    Activations Density 0.015%

    No Known Activations