© 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. 22-GEMMASCOPE-RES-131K
    7. 95629
    Prev
    Next
    INDEX
    Explanations

    code declarations and types

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

    The neuron activates on tokens containing digits—numeric literals or identifiers suffixed with numbers.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     Bâ
    -0.98
     escritores
    -0.96
     выбрать
    -0.93
     mercen
    -0.92
    ......”
    -0.90
     menti
    -0.90
     along
    -0.88
    🅑
    -0.88
     クリーム
    -0.88
     本店
    -0.88
    POSITIVE LOGITS
     now
    1.04
    nější
    0.99
     this
    0.98
     voelt
    0.97
     estadounidenses
    0.91
    omethane
    0.91
     slä
    0.89
    тился
    0.85
     fueran
    0.85
     Leinwand
    0.85
    Activations Density 0.001%

    No Known Activations