© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77167
    Prev
    Next
    INDEX
    Explanations

    keywords and tags

    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
     without
    -0.95
     through
    -0.94
     fairly
    -0.88
     around
    -0.84
    According
    -0.81
     existing
    -0.81
     becoming
    -0.81
     about
    -0.80
     because
    -0.80
     on
    -0.79
    POSITIVE LOGITS
     cuchara
    1.00
    寒い
    0.96
     chiens
    0.96
     MUR
    0.95
     เก
    0.94
    
    0.92
     height
    0.92
     haf
    0.91
     lámpara
    0.90
     INCRE
    0.89
    Activations Density 0.001%

    No Known Activations