© 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. 90967
    Prev
    Next
    INDEX
    Explanations

    purchase, application, uniformity

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

    The neuron is primarily detecting numeric tokens—numbers, dates, measurement values, version or code identifiers, and other digit‐based metadata.

    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
     Tuesday
    -0.70
    ріб
    -0.69
     Late
    -0.68
    inflater
    -0.67
     Presentation
    -0.66
    효
    -0.66
     Ryan
    -0.65
    Late
    -0.65
    sina
    -0.65
     late
    -0.64
    POSITIVE LOGITS
     SSN
    0.74
    돔
    0.69
     Kek
    0.68
     LCA
    0.66
     Muc
    0.65
    ⢦
    0.65
    rieren
    0.65
    ärm
    0.64
     Mesopotamia
    0.64
     exem
    0.63
    Activations Density 0.054%

    No Known Activations