© 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. 19843
    Prev
    Next
    INDEX
    Explanations

    best-known

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

    This neuron fires almost exclusively on the “-known” part of the hyphenated adjective “best-known.”

    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
    鹀
    -1.86
    嵎
    -1.80
    ющими
    -1.80
    それは
    -1.71
     dispuestos
    -1.70
    atively
    -1.66
     táctil
    -1.66
     convencional
    -1.65
    彼らは
    -1.64
    銪
    -1.64
    POSITIVE LOGITS
     Each
    2.22
     in
    2.11
     of
    2.11
    ’
    1.98
     Some
    1.79
     have
    1.63
     These
    1.60
     знаю
    1.59
    exels
    1.58
    \}$,
    1.52
    Activations Density 0.021%

    No Known Activations