© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91809
    Prev
    Next
    INDEX
    Explanations

    wolvesfierce animalspredators

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

    code and markup elements in programming documents or website content.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The main thing this neuron does is pick out numeric tokens (digits and 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
    uldron
    -0.69
     skeletons
    -0.68
    ान
    -0.66
     castles
    -0.65
    рым
    -0.63
     μά
    -0.63
    peka
    -0.63
    ั่ว
    -0.62
    ষ্
    -0.62
     پاس
    -0.61
    POSITIVE LOGITS
     Mayor
    0.98
     Judy
    0.95
     Gaz
    0.89
     fleece
    0.86
     Flash
    0.84
     predators
    0.83
     Mammal
    0.83
    Mayor
    0.82
     mammals
    0.80
    Judy
    0.79
    Activations Density 0.012%

    No Known Activations