© 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. 1823
    Prev
    Next
    INDEX
    Explanations

    numbers in parentheses

    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
    Verb
    -0.78
    +"/"+
    -0.75
    Kü
    -0.73
    Science
    -0.73
     gare
    -0.73
     uart
    -0.73
     SCIENCE
    -0.72
    Freund
    -0.71
    Sü
    -0.71
     rire
    -0.70
    POSITIVE LOGITS
    tep
    0.77
     drop
    0.75
     Eternity
    0.74
    Repository
    0.74
     почему
    0.68
     khung
    0.68
     Pain
    0.66
    ophenyl
    0.66
     progra
    0.66
     Arena
    0.66
    Activations Density 0.032%

    No Known Activations