© 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. 87041
    Prev
    Next
    INDEX
    Explanations

    yarn and fiber processing

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

    The neuron fires strongly on numeric tokens (digits and numbers), such as dates, counts, measurements, percentages, and other quantity expressions.

    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
    ICON
    -0.86
     primers
    -0.76
    }_{\
    -0.76
     pieza
    -0.72
    ""
    -0.71
    .^
    -0.71
     sewing
    -0.71
    .;
    -0.71
    Zunanje
    -0.69
    abdominal
    -0.68
    POSITIVE LOGITS
     ske
    1.02
     dyeing
    1.01
     KAL
    0.93
     yarn
    0.91
     fiber
    0.88
     Fiber
    0.86
    Fiber
    0.85
     Fibre
    0.83
    Fibre
    0.82
     behaving
    0.81
    Activations Density 0.018%

    No Known Activations