© 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. 32262
    Prev
    Next
    INDEX
    Explanations

    multiple occurrences within a period

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

    The main thing this neuron does is detect numeric expressions (digits and multi­digit numbers) in 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
     many
    -1.42
     any
    -1.29
     for
    -1.29
     especially
    -1.13
    很多
    -1.12
    了很多
    -1.07
     even
    -1.06
     their
    -1.01
    :+:
    -0.99
     often
    -0.97
    POSITIVE LOGITS
     jeweils
    2.25
     consecutively
    1.93
     consecutive
    1.87
     within
    1.84
     successively
    1.84
    respectively
    1.82
     respectively
    1.70
    Within
    1.69
    within
    1.68
     innerhalb
    1.67
    Activations Density 0.108%

    No Known Activations