© 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. 109219
    Prev
    Next
    INDEX
    Explanations

    Heisenberg uncertainty principle

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

    The neuron activates strongly on dense information‐theoretic jargon—especially occurrences of “entropy,” “uncertainty,” and related bound terminology.

    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
    *}{
    -0.82
     Fieber
    -0.81
    чики
    -0.73
     روان
    -0.73
    TBD
    -0.73
    感受到
    -0.69
     विश
    -0.69
    endetta
    -0.69
     unanim
    -0.68
     rags
    -0.68
    POSITIVE LOGITS
     uncertainty
    2.20
     Heisenberg
    2.11
     Uncertainty
    2.09
    uncertainty
    1.88
    Uncertainty
    1.81
     uncertainties
    1.48
     incertidumbre
    1.32
     principle
    1.23
     Uncertain
    1.21
     Principle
    1.20
    Activations Density 0.025%

    No Known Activations