© 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. 73762
    Prev
    Next
    INDEX
    Explanations

    <h1> or </h1>

    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
     Châu
    -0.69
    papan
    -0.68
     Schnell
    -0.67
     прото
    -0.67
    langkah
    -0.65
    擒
    -0.63
    чатки
    -0.62
    νες
    -0.62
    液体
    -0.62
    dds
    -0.62
    POSITIVE LOGITS
    ela
    0.68
     ledge
    0.68
    ffrey
    0.67
    ॣ
    0.67
     합
    0.67
     mond
    0.64
    hülle
    0.64
     Macle
    0.62
     hybrids
    0.61
    FUR
    0.61
    Activations Density 0.144%

    No Known Activations