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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 60162
    Prev
    Next
    INDEX
    Explanations

    successful completion

    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
    parame
    -0.80
     Wartawan
    -0.77
    clicking
    -0.77
     certa
    -0.77
     теперь
    -0.76
     Mannschaft
    -0.76
     Grecs
    -0.76
     argparse
    -0.76
     RouterModule
    -0.76
     such
    -0.75
    POSITIVE LOGITS
     success
    1.50
    success
    1.30
     successes
    1.30
    Success
    1.03
     Success
    1.02
     Erfolg
    1.02
    mozilla
    0.97
     성공
    0.90
    uccess
    0.86
    เริ่ม
    0.85
    Activations Density 0.005%

    No Known Activations