© 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. 76671
    Prev
    Next
    INDEX
    Explanations

    mercury vapor lamps and ballasts

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

    The neuron fires strongly on formal patent‐style technical phrases—especially “The present invention relates to” and core device terminology like “high-pressure discharge lamp,” “ceramic tube,” etc.—i.e. boilerplate patent specification language.

    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
     LED
    -0.97
    LED
    -0.80
     khả
    -0.74
    ведена
    -0.73
     COOKIE
    -0.73
    abled
    -0.70
    酶
    -0.70
    leness
    -0.69
     LEDs
    -0.68
    õi
    -0.67
    POSITIVE LOGITS
     ballast
    1.23
    mercury
    1.03
     mercury
    0.91
     Startup
    0.88
     Hg
    0.84
     burner
    0.84
    Mercury
    0.84
    Startup
    0.82
     filaments
    0.81
     warmup
    0.81
    Activations Density 0.043%

    No Known Activations