© 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. 13208
    Prev
    Next
    INDEX
    Explanations

    feedback loop control

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

    The neuron activates on technical mentions of feedback loops or feedback in control systems.

    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
    1
    -1.84
     besonderen
    -1.65
    ↵↵
    -1.64
     einzigen
    -1.48
    4
    -1.42
    コラボ
    -1.41
     even
    -1.34
     when
    -1.34
     одной
    -1.33
    アレル
    -1.33
    POSITIVE LOGITS
    meisterschaften
    1.73
     Feedback
    1.70
     Conexion
    1.65
     Photographie
    1.64
    ꦸ
    1.63
     miniaturka
    1.63
    ではでは
    1.60
    鲼
    1.60
     både
    1.56
     着物
    1.55
    Activations Density 0.064%

    No Known Activations