© 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. 34-GEMMASCOPE-RES-131K
    7. 84543
    Prev
    Next
    INDEX
    Explanations

    adjectives before nouns

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

    The neuron detects numeric tokens (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
    first
    -0.98
     menyes
    -0.92
    two
    -0.89
     brasileiros
    -0.88
    торая
    -0.88
     mengucap
    -0.87
    both
    -0.87
    ignements
    -0.86
    時には
    -0.86
    啓
    -0.83
    POSITIVE LOGITS
    }}_
    0.98
    𝗧
    0.98
    BJP
    0.97
    ácii
    0.95
    []{
    0.94
     Futuro
    0.92
    Biology
    0.89
    endpush
    0.89
     grati
    0.89
     decline
    0.88
    Activations Density 0.065%

    No Known Activations