Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8464
    Prev
    Next
    INDEX
    Explanations

    C++ .hpp header files

    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
     तथा
    -0.95
    roffenen
    -0.92
    𝓋
    -0.86
    latter
    -0.85
     başar
    -0.79
    middot
    -0.78
    льних
    -0.77
    gamepad
    -0.75
     pájaros
    -0.74
     helados
    -0.73
    POSITIVE LOGITS
     marches
    0.83
     revo
    0.81
    ্স
    0.78
    つは
    0.77
     Compañ
    0.77
     prive
    0.77
    anthene
    0.77
    ्रीय
    0.77
     (_)
    0.76
     persa
    0.76
    Activations Density 0.001%

    No Known Activations