© 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. 117559
    Prev
    Next
    INDEX
    Explanations

    numbers around 5

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

    The neuron fires on multi-digit numeric tokens (especially four-digit numbers).

    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
     ķ
    -0.99
    ilität
    -0.96
    ものである
    -0.93
    {
    -0.93
     supuesto
    -0.88
    謬
    -0.87
    GINIA
    -0.87
     supposed
    -0.87
    étoit
    -0.85
    ../../
    -0.84
    POSITIVE LOGITS
    鸸
    1.00
     razón
    0.98
    
    0.95
     fácil
    0.95
    Външни
    0.94
    骉
    0.91
    thoven
    0.90
     eût
    0.90
    刳
    0.90
    と考えて
    0.88
    Activations Density 0.017%

    No Known Activations