© 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. 10-GEMMASCOPE-RES-131K
    7. 15013
    Prev
    Next
    INDEX
    Explanations

    words starting with bun

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

    This neuron detects the character sequence “bun” as a subword (e.g. in names like Bunyavirus, Bunmei, bunazosin, etc.).

    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
    
    -2.88
    咴
    -2.72
     It
    -2.66
    
    -2.64
    ︓
    -2.56
    ，“
    -2.55
    増えて
    -2.52
     trattato
    -2.50
     consentimiento
    -2.42
     sorgfäl
    -2.39
    POSITIVE LOGITS
    <i>
    2.75
    I
    2.39
    c
    2.17
    `
    2.16
    }$
    2.16
    ),
    2.16
    ст
    2.13
    تهى
    2.08
    <b>
    2.05
    見
    2.05
    Activations Density 0.002%

    No Known Activations