© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 65044
    Prev
    Next
    INDEX
    Explanations

    Bud variations

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

    The neuron activates for the prefix "Bud" in words like Buddha, Buddhist, Budapest, and buddies.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron activates on tokens containing the substring “Bud,” detecting occurrences of “Bud” as part of names or terms (e.g. Buddha, Buddhist, Budapest, Buddleja).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    ynek
    -2.88
    x
    -2.70
    einander
    -2.45
    
    -2.44
    翃
    -2.38
    荭
    -2.28
     necessarie
    -2.25
    糴
    -2.25
     elektrische
    -2.25
     probablement
    -2.23
    POSITIVE LOGITS
    *
    3.53
    {
    3.50
     If
    2.72
    '
    2.72
     Should
    2.53
     And
    2.42
    ？！”
    2.34
     Where
    2.31
                    
    2.31
    刧
    2.25
    Activations Density 0.006%

    No Known Activations