© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 25829
    Prev
    Next
    INDEX
    Explanations

    stock market and business

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

    This neuron fires on numeric and related punctuation tokens—digits, numbers, parentheses, percent signs, colons, etc.—i.e. elements of numeric data.

    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
     Dallas
    -0.85
     Vikipedi
    -0.84
     Missouri
    -0.83
    stylers
    -0.81
     Wiktionnaire
    -0.81
    ké
    -0.80
    calli
    -0.79
     Cul
    -0.78
    SLASH
    -0.78
    kä
    -0.77
    POSITIVE LOGITS
     scrip
    1.17
     BSE
    0.89
     betreff
    0.84
     DVR
    0.83
     CMP
    0.83
    NSE
    0.82
     upo
    0.81
     Festive
    0.81
     spół
    0.81
     Wheelchair
    0.81
    Activations Density 0.009%

    No Known Activations