© 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. 10-GEMMASCOPE-RES-131K
    7. 113599
    Prev
    Next
    INDEX
    Explanations

    fundamental physics concepts

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

    The neuron fires on specialized physics terminology or concepts—words and phrases naming particles, fundamental properties, and technical phenomena in physics.

    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
     to
    -1.65
     savu
    -1.50
     RECOMEND
    -1.46
     AUTHORITIES
    -1.37
     „
    -1.33
    ­
    -1.31
     pēc
    -1.24
     getAddress
    -1.23
     viewWillAppear
    -1.23
     for
    -1.22
    POSITIVE LOGITS
     bibir
    1.48
     diseñar
    1.38
     mercancías
    1.36
     comenzar
    1.33
    ケン
    1.33
    ῖν
    1.32
     sustituir
    1.32
    時間も
    1.32
     emprender
    1.32
     reducido
    1.29
    Activations Density 0.155%

    No Known Activations