© 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. 76298
    Prev
    Next
    INDEX
    Explanations

    segmentation fault or SIGABRT

    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
    PRINTF
    -0.76
    етки
    -0.70
    CompoundButton
    -0.69
    駒
    -0.69
    impinan
    -0.68
    ┫
    -0.68
    зит
    -0.68
     aber
    -0.68
    |[]
    -0.68
     ainda
    -0.67
    POSITIVE LOGITS
    WHE
    0.94
    Blues
    0.93
    蓝
    0.92
     Blues
    0.91
     STOP
    0.91
     蓝
    0.91
     WHE
    0.91
     screen
    0.88
     blue
    0.87
    blues
    0.85
    Activations Density 0.056%

    No Known Activations