© 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. 77931
    Prev
    Next
    INDEX
    Explanations

    LG electronics

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

    The neuron fires on sequences of capitalized letters and numbers that denote product model names, version numbers, or technical specifications.

    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
    غاز
    -0.75
    参考に
    -0.73
    alnız
    -0.72
     dataframe
    -0.71
    endalikan
    -0.70
     undo
    -0.69
    рили
    -0.69
    小孩子
    -0.69
     anointed
    -0.69
    unier
    -0.68
    POSITIVE LOGITS
     LG
    1.59
    LG
    1.36
     lg
    1.07
    افي
    0.90
     Optimus
    0.85
     HomeController
    0.79
     Cine
    0.77
     OLED
    0.76
    \}$,
    0.76
     salvación
    0.75
    Activations Density 0.041%

    No Known Activations