© 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. 34-GEMMASCOPE-RES-131K
    4. 11878
    Prev
    Next
    INDEX
    Explanations

    words starting with Bard

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

    The neuron is triggered by the character sequence “bard” (i.e. occurrences of “bard” as part of any word).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     Freak
    -0.74
    AutoScale
    -0.74
     Mortgage
    -0.73
    BUILT
    -0.71
    ラル
    -0.71
     đạp
    -0.71
    ushed
    -0.71
     Wo
    -0.69
    规则
    -0.69
     verbessert
    -0.69
    POSITIVE LOGITS
    Bard
    0.84
     bard
    0.77
    fileID
    0.75
    Fá
    0.73
    ához
    0.72
    ppe
    0.71
     теп
    0.70
     cobran
    0.69
    することは
    0.69
     Avon
    0.68
    Activations Density 0.021%

    No Known Activations