© 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. 32914
    Prev
    Next
    INDEX
    Explanations

    colonial and colony contexts

    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
    ulously
    -0.88
    なんだか
    -0.80
     Tiếng
    -0.79
    formik
    -0.74
     decidi
    -0.73
     команды
    -0.73
     lesen
    -0.73
    の概要
    -0.72
    uve
    -0.72
     coleccion
    -0.72
    POSITIVE LOGITS
     влади
    0.88
    mouseX
    0.86
    COLON
    0.85
     Kolon
    0.83
     vấn
    0.82
     Colonial
    0.82
     oscillators
    0.82
     era
    0.81
    rão
    0.81
     desiring
    0.81
    Activations Density 0.029%

    No Known Activations