© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117195
    Prev
    Next
    INDEX
    Explanations

    musical instruments and repair

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

    The neuron detects numeric tokens—i.e. explicit numbers, measurements, counts, or years—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
     Space
    -0.82
     GENE
    -0.75
    uais
    -0.71
     المعرف
    -0.71
    szön
    -0.71
    usions
    -0.71
     Gegner
    -0.71
    sión
    -0.71
    的空间
    -0.70
    STREAM
    -0.69
    POSITIVE LOGITS
     maker
    1.18
     handmade
    1.14
     makers
    1.13
     instruments
    1.06
     instrument
    1.02
     repair
    0.97
     strumento
    0.93
     Handmade
    0.92
    Instruments
    0.90
     student
    0.88
    Activations Density 0.011%

    No Known Activations