© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 19693
    Prev
    Next
    INDEX
    Explanations

    Schrödinger equation, quantum mechanics, Dirac fermion

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

    The neuron is strongly activated by specialized quantum‐mechanical terminology and symbols (e.g. Schrödinger, Hamiltonian, wave-function, von Neumann) and thus detects highly technical quantum physics/mathematical jargon.

    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
    ኧ
    -2.45
     谁
    -1.77
     recupero
    -1.73
     schermo
    -1.71
     rumore
    -1.70
     stik
    -1.70
     truk
    -1.68
     meravigli
    -1.67
     bluse
    -1.66
    썽
    -1.65
    POSITIVE LOGITS
     větší
    1.84
     ''
    1.84
     ”
    1.79
    一会儿
    1.69
     tons
    1.65
    incón
    1.65
    \
    1.65
     a
    1.61
     for
    1.60
     and
    1.48
    Activations Density 0.015%

    No Known Activations