© 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. 103114
    Prev
    Next
    INDEX
    Explanations

    RealmObject framework framework

    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
     страна
    -1.23
     maneras
    -1.01
    recept
    -0.96
     ہیں۔
    -0.94
    賬
    -0.93
    liegenden
    -0.91
    刳
    -0.91
     desgra
    -0.90
    ichier
    -0.90
    ungkin
    -0.89
    POSITIVE LOGITS
    O
    0.99
    amate
    0.98
    кну
    0.98
    尤其
    0.97
    сну
    0.97
    muir
    0.96
    remacy
    0.94
    pire
    0.94
    the
    0.94
    眼睛
    0.93
    Activations Density 0.003%

    No Known Activations