© 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. 107471
    Prev
    Next
    INDEX
    Explanations

    quantifiable events

    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
     ит
    -1.08
     проє
    -1.02
     leurs
    -0.99
    ريكي
    -0.98
     daß
    -0.92
    ويت
    -0.91
     навіть
    -0.88
     these
    -0.88
     These
    -0.88
    lacoste
    -0.87
    POSITIVE LOGITS
     freshmen
    1.00
     student
    0.99
     reds
    0.99
     adidas
    0.97
     UAV
    0.96
     Universidade
    0.95
     noexcept
    0.94
     laikā
    0.94
    MigrationBuilder
    0.94
    Portail
    0.94
    Activations Density 0.087%

    No Known Activations