© 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. 1462
    Prev
    Next
    INDEX
    Explanations

    numbers, especially 8

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

    The neuron primarily responds to occurrences of numeric tokens (digits or number literals).

    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
     divertidas
    -0.85
     five
    -0.83
     devez
    -0.80
    CreateIndex
    -0.79
     fused
    -0.78
    ät
    -0.77
    posições
    -0.77
     аллер
    -0.76
    ッポン
    -0.75
     पढ़ें
    -0.74
    POSITIVE LOGITS
    8
    2.11
     вось
    1.77
     eighth
    1.70
     viii
    1.63
     VIII
    1.55
    ⑧
    1.50
     eight
    1.49
     EIGHT
    1.45
     acht
    1.43
     Eighth
    1.42
    Activations Density 0.034%

    No Known Activations