© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78811
    Prev
    Next
    INDEX
    Explanations

    appeared first originally

    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
    فرة
    -0.75
    Titus
    -0.72
     so
    -0.72
     restarted
    -0.72
    ázaro
    -0.72
    elsa
    -0.68
     تھے
    -0.67
     Bene
    -0.67
    終わった
    -0.67
    prés
    -0.66
    POSITIVE LOGITS
     appeared
    1.25
     originally
    1.21
    appeared
    1.05
     first
    1.02
     اولین
    1.00
    originally
    0.99
    first
    0.95
     впервые
    0.95
     появились
    0.92
    riott
    0.91
    Activations Density 0.006%

    No Known Activations