© 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. 63053
    Prev
    Next
    INDEX
    Explanations

    website content and code elements

    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
    وفر
    -0.81
    馆
    -0.77
     gekommen
    -0.77
    ி
    -0.76
    ضيف
    -0.73
    ustice
    -0.70
     Hogwarts
    -0.69
    劳动
    -0.68
     epidermal
    -0.68
    Coal
    -0.67
    POSITIVE LOGITS
    )|(
    0.73
     rez
    0.65
    Ὀ
    0.64
     dood
    0.63
    Тогда
    0.63
    ())).
    0.63
    šta
    0.62
     Coli
    0.62
     Prins
    0.62
     Practices
    0.62
    Activations Density 0.063%

    No Known Activations