© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 55820
    Prev
    Next
    INDEX
    Explanations

    TV shopping offers

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

    The neuron fires on tokens that are part of corporate, brand, or organization names (including their common abbreviations or domain fragments).

    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
    reit
    -0.75
     Тара
    -0.69
    ren
    -0.68
    inquirer
    -0.68
     ausgezeichnet
    -0.68
    fristig
    -0.67
    经纪
    -0.67
     ПОД
    -0.67
    سرد
    -0.67
    iet
    -0.66
    POSITIVE LOGITS
     TV
    1.62
     shopping
    1.59
     Shopping
    1.53
    shopping
    1.43
     television
    1.40
     telev
    1.40
    Shopping
    1.36
    TV
    1.34
     tv
    1.34
     TSV
    1.32
    Activations Density 0.031%

    No Known Activations