© 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. 2525
    Prev
    Next
    INDEX
    Explanations

    table or tables

    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
    omány
    -0.84
    annten
    -0.73
    Motiv
    -0.71
    Epi
    -0.71
    kapet
    -0.71
    motiv
    -0.69
    Sleeping
    -0.69
    ципа
    -0.69
    żo
    -0.69
    fficiency
    -0.69
    POSITIVE LOGITS
     tables
    2.52
     table
    2.25
     Tables
    2.09
    Tables
    2.03
    tables
    1.80
    Table
    1.79
     Table
    1.67
     TABLES
    1.63
    テーブル
    1.57
    TABLES
    1.52
    Activations Density 0.017%

    No Known Activations