© 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. 63776
    Prev
    Next
    INDEX
    Explanations

    Printed circuit boards

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

    The neuron specializes in spotting patent-style claim or specification text, particularly the numbered, parenthesized, and highly formalized enumerations of elements.

    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
     championnat
    -1.08
    อร่อย
    -0.94
    ulence
    -0.93
    racite
    -0.92
     ehre
    -0.91
     dře
    -0.90
     firewood
    -0.90
    atified
    -0.88
    🏟
    -0.87
    ཊ
    -0.87
    POSITIVE LOGITS
     solder
    1.54
     PCB
    1.18
     board
    1.16
     Printed
    1.12
     Solder
    1.04
     boards
    1.01
     soldering
    0.99
     silks
    0.97
    PCB
    0.96
     fiduci
    0.94
    Activations Density 0.182%

    No Known Activations