© 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. 83200
    Prev
    Next
    INDEX
    Explanations

    public, private, static code declarations

    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
     last
    -1.00
    一个
    -0.88
     outro
    -0.86
    有
    -0.82
    чня
    -0.77
     {
    -0.77
    Todo
    -0.77
    ذي
    -0.77
    🎙
    -0.76
    getLast
    -0.76
    POSITIVE LOGITS
    verifier
    0.90
     فيها
    0.88
    ooka
    0.87
    ტი
    0.81
    ופן
    0.81
     caisse
    0.80
     kisses
    0.79
    irci
    0.79
     fenêtre
    0.78
    に入った
    0.78
    Activations Density 0.011%

    No Known Activations