© 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. 22-GEMMASCOPE-RES-131K
    7. 11510
    Prev
    Next
    INDEX
    Explanations

    C++ std::vector and string manipulation

    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_22/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
     otorga
    -1.06
     entweder
    -1.02
     acompaña
    -0.98
     ubica
    -0.94
     všetko
    -0.94
     možno
    -0.94
     пев
    -0.93
     situações
    -0.93
     permitem
    -0.91
     brinda
    -0.89
    POSITIVE LOGITS
     fria
    1.17
     valde
    1.00
    axios
    1.00
     teus
    0.98
    mongoose
    0.98
     renova
    0.94
     orel
    0.92
     péro
    0.90
     argumenta
    0.90
     fios
    0.88
    Activations Density 0.008%

    No Known Activations