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. 7855
    Prev
    Next
    INDEX
    Explanations

    exhaust systems and components

    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
     объясни
    -0.92
    Actually
    -0.90
    Question
    -0.89
    -0.88
    Really
    -0.87
    Who
    -0.83
    Understanding
    -0.82
    Her
    -0.82
    gle
    -0.81
    po
    -0.79
    POSITIVE LOGITS
     manifold
    1.63
    manifold
    1.31
     system
    1.25
     Manif
    1.11
     manifolds
    1.07
    Manif
    1.03
     stroke
    0.94
     pipe
    0.93
    Piz
    0.90
    願い
    0.88
    Activations Density 0.038%

    No Known Activations