© 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. 116712
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     argparse
    -0.80
    ungkap
    -0.77
     getArguments
    -0.76
    ributes
    -0.74
    logio
    -0.73
    УП
    -0.72
    KSI
    -0.72
    oos
    -0.71
     modelAndView
    -0.71
     göster
    -0.70
    POSITIVE LOGITS
     enää
    0.85
    Ꭿ
    0.76
     apache
    0.75
     invests
    0.75
    ಎ
    0.73
    ?)
    0.73
    blu
    0.73
     dolom
    0.71
     निम्
    0.71
     moored
    0.71
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.