© 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. 84272
    Prev
    Next
    INDEX
    Explanations

    surnames ending in berg

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

    The neuron is a high‐activation detector for the character sequence “berg” within tokens.

    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
    x
    -2.53
    "
    -2.39
     was
    -2.27
    '
    -2.25
     they
    -2.19
    在我的
    -2.14
    >
    -2.11
    [
    -2.09
    的了
    -2.06
    +
    -1.97
    POSITIVE LOGITS
    罴
    2.97
    ῞
    2.95
    ية
    2.88
    趼
    2.61
    ۶
    2.59
     appalling
    2.58
    嚒
    2.55
    ﹍﹍
    2.50
    鸶
    2.50
     Gedanke
    2.42
    Activations Density 0.008%

    No Known Activations