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. 8415
    Prev
    Next
    INDEX
    Explanations

    insurance policy terms and conditions

    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
    EditorBrowsable
    -0.80
     LIVES
    -0.80
    lives
    -0.79
    Acetone
    -0.77
    ối
    -0.77
     január
    -0.77
     Hautes
    -0.75
     Mosley
    -0.74
    lassen
    -0.73
     lives
    -0.72
    POSITIVE LOGITS
     layers
    1.23
     layer
    1.18
     Layers
    1.03
     exhaustion
    0.98
     limits
    0.98
     Layer
    0.96
    layers
    0.96
     layering
    0.95
    Limits
    0.94
     triggered
    0.91
    Activations Density 0.008%

    No Known Activations