© 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. 57721
    Prev
    Next
    INDEX
    Explanations

    brand names

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

    The neuron activates on occurrences of product or company brand 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
     científicas
    -0.98
    tică
    -0.91
    mickey
    -0.86
    懌
    -0.85
     hígado
    -0.84
    Quién
    -0.84
    blessed
    -0.83
    apartament
    -0.83
     architekt
    -0.83
    tatuajes
    -0.83
    POSITIVE LOGITS
     brand
    1.06
    牌
    0.95
     branded
    0.94
     generic
    0.93
    brand
    0.90
    Generic
    0.89
     роста
    0.84
     focused
    0.79
    generic
    0.77
    Hear
    0.77
    Activations Density 0.004%

    No Known Activations