© 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. 78821
    Prev
    Next
    INDEX
    Explanations

    MHD stability, clinical, physics variables

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

    scientific and technical terminology related to physics, particularly plasma physics and nuclear physics.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The main thing this neuron does is detect specialized plasma‐physics and fusion research terminology (e.g. “tokamak,” “MHD,” “cyclotron,” “ion‐Larmor,” etc.).

    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
     Heer
    -0.78
    Archie
    -0.75
     ApiService
    -0.74
    ortho
    -0.71
     Fabrik
    -0.71
     Fabri
    -0.70
    rodalom
    -0.69
     bucal
    -0.69
    joit
    -0.69
     KZ
    -0.68
    POSITIVE LOGITS
     equilibrium
    0.86
     Equilibrium
    0.82
     Monticello
    0.80
     Tunisia
    0.79
    efit
    0.77
    فصل
    0.75
    Collabor
    0.74
    печат
    0.74
     Cyclone
    0.74
     mencer
    0.73
    Activations Density 0.012%

    No Known Activations