© 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. 9305
    Prev
    Next
    INDEX
    Explanations

    car brands, surnames, countries

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

    This neuron detects numeric tokens (numbers, including integers and decimals) 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_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
     which
    -0.99
     attiva
    -0.96
     necessity
    -0.94
     debole
    -0.93
     kvalit
    -0.90
     esterna
    -0.89
     vectorielle
    -0.89
    During
    -0.88
     giusta
    -0.86
     available
    -0.85
    POSITIVE LOGITS
    ñas
    0.92
    вся
    0.87
    0.86
    atul
    0.85
    aros
    0.82
    水道
    0.81
    others
    0.80
    amica
    0.79
     הש
    0.77
    acionales
    0.76
    Activations Density 0.019%

    No Known Activations