© 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. 84475
    Prev
    Next
    INDEX
    Explanations

    numbers and scores

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

    The neuron fires on multi-digit number tokens (i.e. numeric figures rather than words).

    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
     thirties
    -0.96
     forties
    -0.79
     cuarenta
    -0.79
     Thirty
    -0.78
    Thirty
    -0.77
     fifties
    -0.75
     Forty
    -0.74
     cincuenta
    -0.71
     twenties
    -0.69
     forty
    -0.68
    POSITIVE LOGITS
     ninety
    1.88
     Ninety
    1.56
    9
    1.53
     eighty
    1.41
     Eighty
    1.16
    Nin
    1.14
     ۹
    1.13
    8
    1.09
    hundred
    1.05
     hundred
    1.03
    Activations Density 0.088%

    No Known Activations