© 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. 44815
    Prev
    Next
    INDEX
    Explanations

    expansion

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

    This neuron responds to instances of the word “expansion.”

    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
    '
    -2.42
    *
    -2.42
     یا
    -2.39
    of
    -2.23
     brasil
    -2.19
    ︕
    -2.17
     spagnolo
    -2.17
    鬭
    -2.16
     estadounid
    -2.13
     acquainted
    -2.09
    POSITIVE LOGITS
    ized
    2.58
     detaylı
    2.45
     koruyucu
    2.30
     gewisser
    2.28
     tzw
    2.25
    姈
    2.23
    ⟞
    2.23
    趼
    2.22
    ization
    2.22
    ↵
    2.22
    Activations Density 0.006%

    No Known Activations