© 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. 19639
    Prev
    Next
    INDEX
    Explanations

    creator/creators

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

    The neuron detects mentions of the word “creator” (including its plural form “creators”).

    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
    AddTagHelper
    -2.48
    粜
    -2.34
    ".
    -2.28
    新款
    -2.19
    的首
    -2.19
    ramientas
    -2.16
    ☫
    -2.14
    骉
    -2.14
    饜
    -2.11
     CGRectMake
    -2.09
    POSITIVE LOGITS
     vorigen
    2.61
     They
    2.36
     “[
    2.27
     However
    2.22
     “(
    2.20
     “
    2.13
    して
    2.06
    to
    2.05
     проводить
    2.03
     Lack
    1.99
    Activations Density 0.004%

    No Known Activations