© 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. 81663
    Prev
    Next
    INDEX
    Explanations

    section headers and dates

    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
    тить
    -0.73
     Fleck
    -0.71
     humbled
    -0.69
    强
    -0.69
     actions
    -0.68
     Verwaltungs
    -0.68
     强
    -0.68
    cass
    -0.67
     раз
    -0.66
     action
    -0.66
    POSITIVE LOGITS
    Runner
    0.94
     Runner
    0.92
    runner
    0.92
    glue
    0.87
    Patricia
    0.85
     Dolphins
    0.85
     glue
    0.84
     autonome
    0.82
    tifies
    0.81
    ogno
    0.81
    Activations Density 0.002%

    No Known Activations