© 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. 8334
    Prev
    Next
    INDEX
    Explanations

    auxiliary commands and terms

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

    The neuron activates on the three-letter sequence “aux” (e.g. in tokens like “aux,” “Aux,” or as part of longer words containing “aux”).

    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
    鄜
    -2.64
    錸
    -2.33
    瑨
    -2.30
    鼕
    -2.25
    ’
    -2.22
    骘
    -2.22
    _{
    -2.19
    푣
    -2.19
    快速的
    -2.17
    何况
    -2.14
    POSITIVE LOGITS
    at
    2.63
    The
    2.58
     μην
    2.45
    of
    2.39
    嫵
    2.38
     stark
    2.34
    to
    2.23
     作り方
    2.20
    riedenheit
    2.20
    </h4>
    2.19
    Activations Density 0.001%

    No Known Activations