© 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. 55892
    Prev
    Next
    INDEX
    Explanations

    stream protocols, technologies, and terms

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

    The neuron fires on the letters “un” immediately followed by “publish” – i.e. it detects occurrences of the word “unpublish.”

    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
     interacts
    -0.70
    uger
    -0.66
    Sediment
    -0.63
     券
    -0.61
     crowdfunding
    -0.61
     Barbara
    -0.61
     aired
    -0.60
    料金
    -0.60
    Exe
    -0.60
     Exe
    -0.60
    POSITIVE LOGITS
     RTP
    1.27
    RTP
    1.00
    USDT
    0.92
    knex
    0.84
    rtp
    0.83
    CIF
    0.81
     лы
    0.81
    СП
    0.79
     CIF
    0.78
    Ice
    0.77
    Activations Density 0.018%

    No Known Activations