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. 7843
    Prev
    Next
    INDEX
    Explanations

    ant attitude, irrigation engineer

    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
     Whilst
    -1.34
     whilst
    -1.30
     மற்ற
    -1.20
    Whilst
    -1.11
     amongst
    -1.05
     ولك
    -1.05
     Amongst
    -1.04
     skall
    -0.98
    ज़
    -0.96
    "?>
    -0.95
    POSITIVE LOGITS
     
    1.27
    为何
    0.96
     Benz
    0.93
    不少
    0.93
    ९
    0.89
     yester
    0.88
    だが
    0.87
    undum
    0.87
     motorists
    0.85
    ushin
    0.85
    Activations Density 0.016%

    No Known Activations