© 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. 123541
    Prev
    Next
    INDEX
    Explanations

    words starting with bo

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

    The neuron flags any token containing the character sequence “bo.”

    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
    CHREIB
    -3.11
     $\&$
    -2.78
    bernador
    -2.66
    ’，
    -2.66
    猹
    -2.64
     „,
    -2.64
    when
    -2.53
    茕
    -2.52
     kumar
    -2.50
    lossians
    -2.50
    POSITIVE LOGITS
    {
    5.06
     be
    3.02
    *
    2.95
    ."
    2.80
    ",
    2.80
     &
    2.73
    `
    2.67
     {
    2.61
    ',
    2.58
    2
    2.58
    Activations Density 0.004%

    No Known Activations