© 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. 76010
    Prev
    Next
    INDEX
    Explanations

    shop, submit, death, handlers

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

    The neuron strongly responds to 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
    diens
    -0.83
     Jenner
    -0.77
    univer
    -0.77
    ecommerce
    -0.74
    oks
    -0.72
    わない
    -0.70
     tenta
    -0.69
    nä
    -0.69
    odi
    -0.68
     Villiers
    -0.68
    POSITIVE LOGITS
     submit
    0.94
     Submit
    0.94
     submissions
    0.91
     frontend
    0.88
    Submit
    0.87
     submission
    0.85
     Submissions
    0.85
     claimant
    0.85
    जब
    0.84
     submitting
    0.83
    Activations Density 0.002%

    No Known Activations