© 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. 98595
    Prev
    Next
    INDEX
    Explanations

    code builder build rebuild

    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
     қара
    -0.77
     paiement
    -0.74
    ڵ
    -0.73
     pés
    -0.73
     soprattutto
    -0.73
     тү
    -0.72
    iczny
    -0.71
    یف
    -0.70
     autoridad
    -0.69
     pelicula
    -0.69
    POSITIVE LOGITS
    builder
    1.46
     builder
    1.38
    Builder
    1.30
     Builder
    1.07
     builders
    1.03
     rebuilding
    0.94
     Async
    0.93
    Widget
    0.87
     rebuild
    0.87
     BUILD
    0.84
    Activations Density 0.000%

    No Known Activations