© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7320
    Prev
    Next
    INDEX
    Explanations

    web addresses and domains

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

    The neuron activates on tokens that are part of publication or website names (e.g. magazine titles, domains, blog or news site identifiers).

    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
    推特
    -1.01
     EEUU
    -0.82
     tourists
    -0.81
    佥
    -0.81
     Internacional
    -0.81
     Američ
    -0.79
    Источник
    -0.79
     Canadá
    -0.78
    ngilizce
    -0.78
     germs
    -0.78
    POSITIVE LOGITS
     Horoscope
    0.94
     doctrina
    0.86
    iffe
    0.85
     adoles
    0.84
     descobrir
    0.84
     CAMPUS
    0.83
     již
    0.82
     Actu
    0.82
     Lifestyle
    0.82
     news
    0.82
    Activations Density 0.023%

    No Known Activations