© 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. 116861
    Prev
    Next
    INDEX
    Explanations

    programming code syntax

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

    This neuron specializes in spotting standalone multi‐digit numeric literals (large numbers) 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
     that
    -1.35
     by
    -1.04
     world
    -0.94
     to
    -0.94
     Wirken
    -0.89
     especialmente
    -0.88
     replacement
    -0.88
    ẩn
    -0.86
    粹
    -0.84
     aunque
    -0.83
    POSITIVE LOGITS
    lamento
    1.00
    
    0.93
     distinguer
    0.91
    getNext
    0.91
     понравился
    0.90
     engelsk
    0.89
     gelingt
    0.88
     mechanistic
    0.87
     pié
    0.86
    👧
    0.86
    Activations Density 0.012%

    No Known Activations