© 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. 115462
    Prev
    Next
    INDEX
    Explanations

    HTML tags with attributes

    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
    ıla
    -0.81
    ək
    -0.79
    âni
    -0.79
    bardziej
    -0.78
    undidad
    -0.77
    jados
    -0.77
    ρέπει
    -0.76
     szary
    -0.76
    Editing
    -0.75
     Along
    -0.75
    POSITIVE LOGITS
    .–
    0.86
    包括
    0.83
     després
    0.83
    rums
    0.83
    span
    0.82
     Faux
    0.81
     Illus
    0.79
    >+</
    0.79
    BackgroundImage
    0.79
     наши
    0.79
    Activations Density 0.034%

    No Known Activations