© 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. 98432
    Prev
    Next
    INDEX
    Explanations

    railroad names and locations

    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
     because
    -1.05
     really
    -1.04
     could
    -1.04
     probably
    -0.99
     sparked
    -0.97
     perpetually
    -0.95
     some
    -0.94
     Often
    -0.93
     sizable
    -0.93
     Really
    -0.92
    POSITIVE LOGITS
    connecting
    1.27
    connects
    1.14
    reaching
    1.13
     delightfully
    1.08
    Connecting
    1.06
     passagers
    1.05
     elegant
    1.04
     remarkably
    1.02
     luscious
    1.02
     pasaj
    1.02
    Activations Density 0.002%

    No Known Activations