© 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. 48242
    Prev
    Next
    INDEX
    Explanations

    auto-generated code comments

    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
    (''),
    -0.74
     diversión
    -0.71
    complicated
    -0.69
     ऐसे
    -0.68
     WHE
    -0.66
     Wheels
    -0.66
    painter
    -0.66
     Coming
    -0.66
    Rollback
    -0.65
    ylon
    -0.65
    POSITIVE LOGITS
     manor
    0.75
     Narrow
    0.73
     mansion
    0.72
    Narrow
    0.72
     plaque
    0.69
    VOA
    0.69
     attrs
    0.69
     editors
    0.69
     البلد
    0.69
     тя
    0.68
    Activations Density 0.043%

    No Known Activations