© 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. 2398
    Prev
    Next
    INDEX
    Explanations

    education and study

    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
    tismo
    -0.92
    īg
    -0.76
    relser
    -0.75
    教
    -0.73
    Navigator
    -0.72
    હે
    -0.72
    edition
    -0.71
    зг
    -0.71
    evaluator
    -0.70
    elezo
    -0.69
    POSITIVE LOGITS
     studied
    3.67
     studying
    3.53
     study
    3.50
    studied
    2.84
     studies
    2.72
    Studying
    2.70
    study
    2.69
     STUDY
    2.64
     Studying
    2.63
    Study
    2.53
    Activations Density 0.110%

    No Known Activations