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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 111951
    Prev
    Next
    INDEX
    Explanations

    names and abbreviations

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

    This neuron activates on tokens starting with “Buk” (e.g., in names like Bukola, Bukhara, or Bukavu).

    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
    d
    -2.88
    на
    -2.80
    x
    -2.59
    en
    -2.56
    g
    -2.55
     he
    -2.52
    v
    -2.50
     is
    -2.47
    of
    -2.45
    b
    -2.45
    POSITIVE LOGITS
    {
    3.50
    鬭
    3.14
     ausein
    2.95
    鑁
    2.86
    鵟
    2.67
    蕯
    2.63
    毉
    2.61
     zü
    2.53
    
    2.50
     rendus
    2.48
    Activations Density 0.013%

    No Known Activations