© 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. 480
    Prev
    Next
    INDEX
    Explanations

    initial/final state particle interactions

    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
     artikkelen
    -0.74
    venska
    -0.70
    ecycle
    -0.69
    вети
    -0.69
    𝗝
    -0.69
    
    -0.69
    ieee
    -0.68
    yntax
    -0.67
    comy
    -0.67
    CYCLE
    -0.66
    POSITIVE LOGITS
     outgoing
    1.38
     incoming
    1.30
     final
    1.26
    outgoing
    1.23
    final
    1.08
     incident
    1.08
    incoming
    1.03
     initial
    1.02
     legs
    1.02
    Final
    0.97
    Activations Density 0.021%

    No Known Activations