© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78019
    Prev
    Next
    INDEX
    Explanations

    backers, exchanges, and performance metrics

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

    The neuron activates on numeric expressions—quantities, prices, dates, percentages, and other digit‐based metrics.

    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
    使用する
    -1.00
    ENTINA
    -0.99
     PHOTO
    -0.99
    様な
    -0.95
    verzeichnis
    -0.93
    andte
    -0.92
     İ
    -0.92
     мальчика
    -0.87
    
    -0.87
    cker
    -0.86
    POSITIVE LOGITS
     ajoutez
    1.09
     choisissez
    1.02
     suivez
    1.00
    ！）
    0.98
     mempelajari
    0.97
    cestry
    0.97
    ！(
    0.96
    
    0.96
     ·
    0.94
    ？）
    0.94
    Activations Density 0.229%

    No Known Activations