© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 53797
    Prev
    Next
    INDEX
    Explanations

    DataType and Collection

    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
     поставить
    -0.71
    niejs
    -0.71
    ilität
    -0.70
    getDoctrine
    -0.69
    อนไลน์
    -0.68
     Fernanda
    -0.68
     نق
    -0.67
     Plays
    -0.66
     origem
    -0.66
     spiele
    -0.66
    POSITIVE LOGITS
     Dunne
    0.68
    tuples
    0.66
     jaw
    0.63
     Rapport
    0.63
     repentance
    0.63
    CreateInfo
    0.63
    лли
    0.62
    喙
    0.62
    ImageView
    0.62
     Aussehen
    0.61
    Activations Density 0.068%

    No Known Activations