© 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. 66243
    Prev
    Next
    INDEX
    Explanations

    elbow

    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
    Pasos
    -0.86
     Villarreal
    -0.81
     engagement
    -0.74
    antina
    -0.73
    拇
    -0.73
     Engagement
    -0.71
    ตา
    -0.69
     přek
    -0.68
    Mejor
    -0.68
     Petrus
    -0.68
    POSITIVE LOGITS
     elbow
    4.28
     elbows
    4.03
     Elbow
    3.17
    elbow
    3.11
    肘
    2.34
    elb
    2.25
     forearm
    1.78
    El
    1.74
     elb
    1.72
     El
    1.56
    Activations Density 0.028%

    No Known Activations