© 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. 34576
    Prev
    Next
    INDEX
    Explanations

    keywords in text

    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
    แม่
    -0.79
    实战
    -0.77
     arrivé
    -0.75
     neum
    -0.75
    ྟ
    -0.74
     tecla
    -0.74
     pretende
    -0.73
    rids
    -0.73
    τό
    -0.73
    iony
    -0.73
    POSITIVE LOGITS
    tific
    0.77
     activated
    0.77
     ene
    0.77
    ѝ
    0.77
     inventory
    0.77
    诲
    0.75
    cidade
    0.74
    <0x83>
    0.74
     active
    0.74
     pod
    0.73
    Activations Density 0.018%

    No Known Activations