© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118915
    Prev
    Next
    INDEX
    Explanations

    Jexus Web Server

    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
     eight
    -0.82
    ZIONI
    -0.80
    impl
    -0.80
     aprile
    -0.78
     so
    -0.78
    iotti
    -0.78
     International
    -0.76
     international
    -0.76
     like
    -0.75
     many
    -0.74
    POSITIVE LOGITS
    ≡
    0.94
     Crédit
    0.93
     REQUIRE
    0.86
    kosten
    0.85
     sien
    0.85
     spesifik
    0.84
    laria
    0.83
     Ukraina
    0.83
    obtained
    0.83
     jub
    0.82
    Activations Density 0.002%

    No Known Activations