© 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. 2381
    Prev
    Next
    INDEX
    Explanations

    those/were brave/foolish

    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
    gründ
    -0.85
     laga
    -0.82
    ləş
    -0.82
    eachtet
    -0.81
    vajú
    -0.79
    Constructors
    -0.77
    sibility
    -0.77
    textarea
    -0.77
    chestra
    -0.77
     enseñanza
    -0.77
    POSITIVE LOGITS
     brave
    2.97
     stupid
    2.55
     smart
    2.47
     foolish
    2.47
     bold
    2.36
     dumb
    2.22
    brave
    2.16
     courageous
    2.05
     silly
    1.95
     unfortunate
    1.91
    Activations Density 0.058%

    No Known Activations