© 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. 92780
    Prev
    Next
    INDEX
    Explanations

    magnetic properties and devices

    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
    elder
    -0.82
    血压
    -0.78
    modelBuilder
    -0.77
    goyle
    -0.74
    _->
    -0.70
    seck
    -0.69
    fromJson
    -0.69
    brides
    -0.68
    akaran
    -0.68
    Rocket
    -0.67
    POSITIVE LOGITS
     magnetic
    4.28
    magnetic
    3.55
     Magnetic
    3.42
    Magnetic
    3.33
    磁
    3.17
     magne
    3.16
     magnetization
    2.98
     magnet
    2.95
     magneto
    2.88
     magnetism
    2.81
    Activations Density 0.198%

    No Known Activations