© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31962
    Prev
    Next
    INDEX
    Explanations

    classical electromagnetic fields

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     kissed
    -0.83
     Geological
    -0.81
    馆
    -0.77
    Planta
    -0.73
     kissing
    -0.72
     Medicaid
    -0.70
    ppb
    -0.70
     baseline
    -0.70
    alamu
    -0.69
     monotonic
    -0.68
    POSITIVE LOGITS
     charge
    0.98
     Poy
    0.97
     magneto
    0.89
     solen
    0.89
     Charge
    0.87
    Charge
    0.86
     charges
    0.85
     electromagnetic
    0.84
    Jpa
    0.84
    chtete
    0.84
    Activations Density 0.013%

    No Known Activations