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. 8374
    Prev
    Next
    INDEX
    Explanations

    computer code and math notation

    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
    atre
    -0.88
     Configuración
    -0.86
    のかも
    -0.86
     numéros
    -0.86
     cze
    -0.85
    itve
    -0.85
    )]=
    -0.83
    也不敢
    -0.83
    раб
    -0.83
     installé
    -0.82
    POSITIVE LOGITS
     Immaculate
    0.94
     obstacles
    0.92
    首次
    0.88
     cioc
    0.86
     abusi
    0.85
    𝑢
    0.83
    镑
    0.81
    ләр
    0.81
     obstacle
    0.81
    tività
    0.79
    Activations Density 0.018%

    No Known Activations