© 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. 79715
    Prev
    Next
    INDEX
    Explanations

    specific phrases and numbers

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

    The neuron activates on numeric tokens, i.e. it detects 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
     families
    -0.88
     takie
    -0.88
     Chaque
    -0.87
     atletas
    -0.83
    ایج
    -0.82
     honlap
    -0.80
     linguistique
    -0.79
    ЙТЕ
    -0.78
     handeln
    -0.78
    一致
    -0.78
    POSITIVE LOGITS
    angol
    0.82
    META
    0.80
     دن
    0.79
    礁
    0.79
     Mult
    0.78
     betyr
    0.78
    ื้น
    0.77
    artifactId
    0.76
     egli
    0.75
    ází
    0.75
    Activations Density 0.003%

    No Known Activations