© 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. 4234
    Prev
    Next
    INDEX
    Explanations

    wikia, fandom wikis, encyclopedias

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

    The neuron strongly activates on substrings of wiki project names (e.g. “Wik,” “ia,” “pedia,” “Bulbapedia,” “Wikia”).

    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
     Actually
    -0.73
     Aero
    -0.72
     actually
    -0.71
     nói
    -0.70
    ague
    -0.70
     Nature
    -0.69
    festival
    -0.68
    шое
    -0.68
    ука
    -0.68
     Gómez
    -0.67
    POSITIVE LOGITS
     fandom
    1.92
     wiki
    1.84
     Wik
    1.71
     Fandom
    1.66
    Fandom
    1.55
    Wik
    1.55
    wikia
    1.46
     Wiki
    1.41
    wiki
    1.38
    fandom
    1.37
    Activations Density 0.025%

    No Known Activations