© 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. 34-GEMMASCOPE-RES-131K
    7. 103745
    Prev
    Next
    INDEX
    Explanations

    control over

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

    This neuron activates on mentions of having “control” (especially phrases like “control over”) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    yorlar
    -0.91
     Overlay
    -0.85
    まれた
    -0.82
    ですかね
    -0.79
    غات
    -0.79
    注釈
    -0.78
    NSIndexPath
    -0.78
     ध्यान
    -0.76
    ydı
    -0.76
     heil
    -0.75
    POSITIVE LOGITS
     over
    4.72
     över
    2.30
     of
    2.30
     над
    2.13
    over
    1.81
     sobre
    1.76
    Over
    1.55
     über
    1.45
     OVER
    1.33
     přes
    1.29
    Activations Density 0.029%

    No Known Activations