© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1165
    Prev
    Next
    INDEX
    Explanations

    drivers, software, technical documentation

    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
    價值
    -0.90
    atás
    -0.86
    Ankara
    -0.81
     trennen
    -0.81
     only
    -0.79
     ممن
    -0.76
     PyLong
    -0.76
     both
    -0.76
    baarheid
    -0.76
    niejsza
    -0.76
    POSITIVE LOGITS
     file
    1.11
     Windows
    0.96
     File
    0.92
    problems
    0.90
    '];
    0.89
     László
    0.89
     troubleshoot
    0.89
    getTimestamp
    0.88
    SOLVED
    0.88
     ये
    0.87
    Activations Density 0.006%

    No Known Activations