© 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. 90249
    Prev
    Next
    INDEX
    Explanations

    types of categories

    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
     bytu
    -0.88
     ''
    -0.86
     malheur
    -0.85
    🛫
    -0.82
    ступил
    -0.80
    getOutputStream
    -0.80
    adomo
    -0.77
    itoneum
    -0.77
    Storia
    -0.76
    ység
    -0.76
    POSITIVE LOGITS
     species
    2.02
     items
    1.83
     genres
    1.80
     diseases
    1.77
     categories
    1.73
     types
    1.73
     commodities
    1.55
     substances
    1.55
     sectors
    1.53
     topics
    1.48
    Activations Density 0.296%

    No Known Activations