© 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. 84164
    Prev
    Next
    INDEX
    Explanations

    numbers and prices

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

    The neuron consistently activates on sequences of digits—that is, on numeric tokens (including integers and numeric substrings).

    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
     that
    -1.31
     by
    -1.02
    جمة
    -0.84
     alignItems
    -0.83
     such
    -0.82
     one
    -0.82
     diverse
    -0.81
    錚
    -0.79
     Folge
    -0.79
    vær
    -0.78
    POSITIVE LOGITS
    gewiesen
    1.00
    んだから
    1.00
     umgangssprach
    0.98
     وقتی
    0.96
    τούν
    0.95
    ὲ
    0.94
    0
    0.94
    ０
    0.92
     offiziell
    0.92
     割
    0.92
    Activations Density 0.047%

    No Known Activations