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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7917
    Prev
    Next
    INDEX
    Explanations

    tensile testing and mechanical properties

    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
     penalty
    -0.77
     Naidu
    -0.75
    虧
    -0.75
     علیه
    -0.72
    uncias
    -0.71
    mura
    -0.70
     Sahib
    -0.70
    gyi
    -0.69
    nay
    -0.69
     Massen
    -0.69
    POSITIVE LOGITS
     tensile
    1.39
     testing
    1.33
     tension
    1.27
     Testing
    1.18
     compression
    1.13
    compression
    1.09
    Testing
    1.06
    Tension
    1.05
     test
    1.02
     tests
    1.02
    Activations Density 0.026%

    No Known Activations