© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1100
    Prev
    Next
    INDEX
    Explanations

    programming exercises, assignments

    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
     malang
    -0.91
     ApiService
    -0.87
     Saltar
    -0.87
     Compte
    -0.85
     Equipe
    -0.84
     maaf
    -0.83
     initData
    -0.82
    🧐
    -0.82
    embroidered
    -0.82
     分析
    -0.82
    POSITIVE LOGITS
     exercise
    1.66
     practice
    1.66
     assignment
    1.41
     homework
    1.39
     exercises
    1.37
     Exercise
    1.34
    practice
    1.30
     practise
    1.23
     Practice
    1.23
     Assignment
    1.17
    Activations Density 0.065%

    No Known Activations