© 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. 34-GEMMASCOPE-RES-131K
    4. 45396
    Prev
    Next
    INDEX
    Explanations

    spin transport and accumulation

    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
     Glove
    -0.73
    tape
    -0.73
     Intelligen
    -0.72
    rapp
    -0.70
    ătă
    -0.70
     combustion
    -0.70
    ვი
    -0.69
     Duckworth
    -0.69
    路线
    -0.69
     kwanza
    -0.69
    POSITIVE LOGITS
     drift
    1.13
     Drift
    1.10
     Ons
    1.05
     driven
    1.02
     transport
    0.99
     Driven
    0.94
     driving
    0.91
    Ons
    0.88
     drifts
    0.87
     current
    0.87
    Activations Density 0.081%

    No Known Activations