© 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. 117768
    Prev
    Next
    INDEX
    Explanations

    Wednesday

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

    The neuron strongly activates on numeric tokens (digit sequences) wherever they appear in code or markup.

    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
     kedua
    -0.91
    unzione
    -0.76
    baca
    -0.75
    Dk
    -0.73
    يلات
    -0.70
    browserify
    -0.70
    prototype
    -0.69
    ཨ
    -0.69
     shalt
    -0.68
    zés
    -0.68
    POSITIVE LOGITS
             
    1.95
     Wednesday
    1.38
    Wednesday
    1.23
     iii
    1.05
     mercredi
    1.02
    --------
    1.00
    iii
    1.00
     WEDNESDAY
    0.96
     trio
    0.96
     Penang
    0.91
    Activations Density 0.052%

    No Known Activations