© 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. 103227
    Prev
    Next
    INDEX
    Explanations

    Opening Day starts

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

    The neuron fires on numerical tokens—digits and multi‐digit numbers representing stats, counts, or measures.

    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
     всичко
    -0.75
    Wick
    -0.74
    жені
    -0.73
    pkins
    -0.71
    Sommaire
    -0.70
    बंध
    -0.69
    低声
    -0.69
    слови
    -0.68
    ıs
    -0.68
     Herausgeber
    -0.67
    POSITIVE LOGITS
     start
    3.02
     starting
    2.58
     starts
    2.56
     Start
    2.28
    Start
    2.27
    start
    2.25
     started
    2.16
    START
    1.98
    Starts
    1.91
     Starts
    1.90
    Activations Density 0.015%

    No Known Activations