© 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. 41950
    Prev
    Next
    INDEX
    Explanations

    but- prefix or part of chemical names

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

    surnames that begin with "But" (like Butts, Buttazoni, Buttigieg, etc.).

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

    The neuron strongly activates on tokens containing the substring “but,” especially when it appears at the start of a token.

    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
    O
    -2.69
     of
    -2.48
    at
    -2.39
    il
    -2.33
    ids
    -2.30
     t
    -2.28
    id
    -2.20
     ї
    -2.13
    I
    -2.08
    P
    -2.03
    POSITIVE LOGITS
    祤
    2.78
    嵓
    2.64
    ים
    2.64
    ⃤
    2.41
    餿
    2.41
     verhind
    2.39
    xiii
    2.34
    mpagne
    2.30
    珵
    2.30
    を目指す
    2.28
    Activations Density 0.021%

    No Known Activations