© 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. 9494
    Prev
    Next
    INDEX
    Explanations

    milling and extrusion processes

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

    The neuron fires on words referring to mills and milling or grinding equipment and processes.

    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
    ↵
    -2.52
    幾乎
    -2.36
    In
    -2.31
    The
    -2.20
    輒
    -2.11
     been
    -2.09
    ：「
    -2.05
    ’
    -1.98
     crowning
    -1.98
     был
    -1.94
    POSITIVE LOGITS
    釭
    2.50
     '
    2.22
    茕
    2.17
    ⎔
    2.16
     itſelf
    2.16
     Anſ
    2.11
    沕
    2.11
    崀
    2.09
    圌
    2.06
     invitar
    2.02
    Activations Density 0.007%

    No Known Activations