© 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. 34874
    Prev
    Next
    INDEX
    Explanations

    Objective-C/C++ type declarations

    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
     so
    -0.85
     weir
    -0.81
    TInt
    -0.80
     计划
    -0.80
    ながらも
    -0.79
     дальше
    -0.77
     but
    -0.77
    Custo
    -0.76
    rfan
    -0.75
    Quasi
    -0.75
    POSITIVE LOGITS
     typeof
    1.07
    könyv
    1.05
    íteni
    1.02
    ☕
    0.98
    struct
    0.95
    ͦ
    0.95
    typeof
    0.93
    ïdes
    0.91
    void
    0.88
    bleiben
    0.88
    Activations Density 0.007%

    No Known Activations