© 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. 10-GEMMASCOPE-RES-131K
    4. 9902
    Prev
    Next
    INDEX
    Explanations

    Diocese, Silurus, Denhamia, Eumitra, PowerEdge

    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_10/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
     AGUA
    -1.72
     Inclu
    -1.61
    Nouvelle
    -1.60
    茈
    -1.60
    zonder
    -1.56
     Condens
    -1.56
     Congreg
    -1.54
    notated
    -1.51
     Joko
    -1.51
     requerimientos
    -1.49
    POSITIVE LOGITS
     for
    2.05
     "
    1.93
     Since
    1.65
     также
    1.61
     also
    1.53
     in
    1.48
     '
    1.48
     jeweils
    1.47
     Recently
    1.47
    Also
    1.45
    Activations Density 0.127%

    No Known Activations