© 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. 92563
    Prev
    Next
    INDEX
    Explanations

    Irish places and structures

    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
    titleMargin
    -0.88
    edil
    -0.79
    Toll
    -0.78
    <0xD8>
    -0.75
     separados
    -0.73
     keyCode
    -0.72
    Réponse
    -0.71
    働
    -0.71
    IFont
    -0.71
    jScrollPane
    -0.70
    POSITIVE LOGITS
     BER
    0.82
    ネットワーク
    0.79
    PTION
    0.76
     Barbosa
    0.72
     SPRINGS
    0.72
    PRESSION
    0.71
    ativ
    0.71
     interne
    0.70
     inca
    0.69
     tamu
    0.69
    Activations Density 0.004%

    No Known Activations