© 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. 10-GEMMASCOPE-RES-131K
    4. 105784
    Prev
    Next
    INDEX
    Explanations

    arena fighting and tournaments

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

    The neuron responds to tokens containing the character sequence “io.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     CATALOG
    -1.64
     =
    -1.54
     lele
    -1.48
    ‪.‬‬
    -1.48
     peugeot
    -1.47
     and
    -1.46
     ⓒ
    -1.46
    グルト
    -1.45
     perry
    -1.44
     fince
    -1.44
    POSITIVE LOGITS
    s
    1.50
     sév
    1.47
    尤其
    1.46
     We
    1.44
    蓠
    1.41
     fréquent
    1.37
    焌
    1.37
     vuelven
    1.37
     Where
    1.36
     WaitForSeconds
    1.36
    Activations Density 0.010%

    No Known Activations