© 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. 81146
    Prev
    Next
    INDEX
    Explanations

    segmentation fault or blame

    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
    BROOK
    -0.82
    /*!
    -0.80
    ће
    -0.79
    Password
    -0.79
     eſſ
    -0.77
    Bern
    -0.76
    UTHER
    -0.75
    க
    -0.74
    ার্
    -0.74
    تر
    -0.73
    POSITIVE LOGITS
     fault
    7.28
    fault
    5.25
     Fault
    4.97
    Fault
    4.56
    FAULT
    3.55
     faults
    3.36
     blame
    3.03
    faults
    2.47
     faute
    2.44
     culpa
    2.30
    Activations Density 0.029%

    No Known Activations