© 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. 34-GEMMASCOPE-RES-131K
    7. 117544
    Prev
    Next
    INDEX
    Explanations

    superconductivity

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

    The neuron fires on dense technical terms and jargon from condensed‐matter physics papers—especially words related to superconductivity and its phenomena.

    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
     coalition
    -0.78
     WING
    -0.75
    mahan
    -0.71
     stmt
    -0.71
    youth
    -0.71
     Citrus
    -0.70
    Fitted
    -0.70
    crackers
    -0.70
    Soda
    -0.69
    Steak
    -0.68
    POSITIVE LOGITS
     super
    2.11
     superconducting
    2.08
    super
    1.94
    Super
    1.85
     Super
    1.80
    SUPER
    1.49
    スーパー
    1.48
     SUPER
    1.42
     супер
    1.41
    超
    1.28
    Activations Density 0.089%

    No Known Activations