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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99701
    Prev
    Next
    INDEX
    Explanations

    import statements and code structure

    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
     TabLayout
    -0.99
     because
    -0.90
    obacter
    -0.85
    TintMode
    -0.76
     foundational
    -0.76
    setCharacter
    -0.76
    CreateTable
    -0.75
    zp
    -0.75
     any
    -0.75
     blir
    -0.74
    POSITIVE LOGITS
    import
    1.71
     void
    1.53
    class
    1.39
     import
    1.38
    void
    1.30
     class
    1.29
    Import
    1.05
     importing
    1.02
     Import
    1.00
     imports
    0.98
    Activations Density 0.003%

    No Known Activations