© 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. 71353
    Prev
    Next
    INDEX
    Explanations

    symbols and code snippets

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

    The neuron is triggered by numeric tokens (integers or decimals), i.e. it spots literal 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_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
     kapit
    -1.11
     parut
    -1.08
     exceptionnel
    -1.02
    फ़
    -1.01
     kommunik
    -1.00
     absolue
    -0.98
     alkoh
    -0.98
     hiburan
    -0.98
     recorte
    -0.98
    où
    -0.98
    POSITIVE LOGITS
    ߰
    0.99
    他們的
    0.96
     універ
    0.95
    endish
    0.94
     Malvern
    0.94
    fficients
    0.94
     різних
    0.92
     CRP
    0.91
    Puss
    0.91
     hispanic
    0.90
    Activations Density 0.002%

    No Known Activations