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. 8376
    Prev
    Next
    INDEX
    Explanations

    how something will fare or affect

    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
    成为
    -0.88
    得到
    -0.86
    Оста
    -0.85
    origen
    -0.85
    才有
    -0.85
     ہو
    -0.85
     Entstehung
    -0.82
    हरा
    -0.81
     tạo
    -0.81
     mít
    -0.80
    POSITIVE LOGITS
     fared
    1.43
     fare
    1.38
     react
    1.27
     compares
    1.23
     compare
    1.16
     affect
    1.13
     reaccion
    1.12
     feel
    1.11
     reacted
    1.11
     fares
    1.09
    Activations Density 0.043%

    No Known Activations