© 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. 77467
    Prev
    Next
    INDEX
    Explanations

    electronics brands and products

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

    This neuron fires on uppercase sequences denoting brand, company, or product model names.

    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
     آیفون
    -0.83
    classID
    -0.72
    HttpEntity
    -0.70
     cnc
    -0.68
    皇后
    -0.66
    iembrie
    -0.65
    🌜
    -0.65
     biodiesel
    -0.65
    templateUrl
    -0.64
    dent
    -0.63
    POSITIVE LOGITS
     Samsung
    2.31
     Philips
    2.28
     Sony
    2.09
     Toshiba
    1.95
     Panasonic
    1.85
     LG
    1.82
    Philips
    1.79
    Samsung
    1.75
     Siemens
    1.67
    Sony
    1.56
    Activations Density 0.100%

    No Known Activations