© 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. 84366
    Prev
    Next
    INDEX
    Explanations

    chapter or section number

    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
    ของ
    -0.94
    넉
    -0.93
     داشتند
    -0.89
     никаких
    -0.88
     eenvou
    -0.88
     Ayuda
    -0.88
     赵
    -0.88
    вають
    -0.87
     thánh
    -0.87
    beitet
    -0.86
    POSITIVE LOGITS
     four
    0.98
     three
    0.93
     -
    0.93
     –
    0.93
    —
    0.92
     one
    0.90
     things
    0.87
    ねて
    0.85
     dzięki
    0.83
     freaking
    0.82
    Activations Density 0.023%

    No Known Activations