© 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. 77659
    Prev
    Next
    INDEX
    Explanations

    SIGABRT error

    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
     INSTALLATION
    -0.83
     ー
    -0.80
     Princeton
    -0.79
    ℗
    -0.77
     benar
    -0.76
     computation
    -0.76
    isConnected
    -0.75
    Princeton
    -0.75
    вни
    -0.73
    Installation
    -0.72
    POSITIVE LOGITS
     ২০১
    0.88
     lessor
    0.86
     GIL
    0.78
    ئم
    0.74
    楼
    0.73
     Additive
    0.73
     EDI
    0.72
     jockey
    0.72
     libs
    0.72
     درون
    0.71
    Activations Density 0.031%

    No Known Activations