© 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. 10-GEMMASCOPE-RES-131K
    7. 104875
    Prev
    Next
    INDEX
    Explanations

    Bud Spencer

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

    The neuron activates on occurrences of the sequence “Bud” (i.e. tokens beginning with or containing “Bud”).

    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
    翃
    -3.84
     unrival
    -2.86
    籏
    -2.77
    e
    -2.75
     descub
    -2.64
    毳
    -2.61
     houver
    -2.58
    鶿
    -2.58
     frequentemente
    -2.56
     professores
    -2.53
    POSITIVE LOGITS
    {
    4.50
    What
    3.11
     If
    3.11
    荩
    2.88
    ي
    2.83
    While
    2.64
    >
    2.56
    们的
    2.56
    One
    2.45
     Where
    2.44
    Activations Density 0.004%

    No Known Activations