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. 8224
    Prev
    Next
    INDEX
    Explanations

    introductions and questions

    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
     STUDENTS
    -1.16
     QUE
    -1.05
    ของคุณ
    -1.04
    stellungen
    -1.00
    uccess
    -0.98
     Você
    -0.96
    hopefully
    -0.96
     marquer
    -0.95
     проводится
    -0.95
    powering
    -0.94
    POSITIVE LOGITS
     the
    1.62
     can
    1.49
     have
    1.33
     include
    1.30
     be
    1.25
     need
    1.24
     cannot
    1.18
     after
    1.16
     described
    1.14
     because
    1.13
    Activations Density 0.011%

    No Known Activations