© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 45217
    Prev
    Next
    INDEX
    Explanations

    magnetic field topology

    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
    insegna
    -0.88
    stals
    -0.86
    dyr
    -0.78
     微
    -0.77
     Kyr
    -0.77
    🐋
    -0.76
    ETTI
    -0.76
    ITT
    -0.75
     فلسطين
    -0.70
    Neden
    -0.70
    POSITIVE LOGITS
     magnetic
    1.01
     Magnetic
    0.90
    Magnetic
    0.86
     topology
    0.84
     MAGNET
    0.80
    magnetic
    0.76
     retorna
    0.75
     själ
    0.73
     Smart
    0.71
     open
    0.70
    Activations Density 0.021%

    No Known Activations