© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 111281
    Prev
    Next
    INDEX
    Explanations

    operator actions

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

    The neuron strongly activates on the word “operator” (i.e. references to the machine or system operator).

    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
     for
    -1.60
     Our
    -1.53
     berühmten
    -1.47
     We
    -1.41
     Hinblick
    -1.38
    </h4>
    -1.35
     otras
    -1.35
     their
    -1.33
     in
    -1.31
     eigentlichen
    -1.28
    POSITIVE LOGITS
    ǎ
    1.48
    Etimología
    1.45
    nių
    1.45
     отношениях
    1.44
    ophageal
    1.44
    Like
    1.43
    一趟
    1.42
    狆
    1.42
     насла
    1.41
    Жит
    1.41
    Activations Density 0.040%

    No Known Activations