© 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. 55916
    Prev
    Next
    INDEX
    Explanations

    report details and questions

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

    The neuron specializes in spotting numeric literals (i.e. sequences of digits) in the text.

    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
    鳟
    -0.81
    ៅ
    -0.80
     vícti
    -0.75
    Eacute
    -0.71
     cask
    -0.70
    Wholesale
    -0.69
    Warriors
    -0.69
    submenu
    -0.69
     Wich
    -0.69
    ставки
    -0.69
    POSITIVE LOGITS
    Detail
    1.09
     detail
    1.09
     footer
    1.00
    detail
    0.99
     Detail
    0.97
    Band
    0.96
     repeating
    0.94
     Header
    0.94
     Band
    0.92
     repeated
    0.92
    Activations Density 0.043%

    No Known Activations