© 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. 33567
    Prev
    Next
    INDEX
    Explanations

    university departments and majors

    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
     hés
    -0.81
    ụn
    -0.80
     manteau
    -0.77
    にします
    -0.77
     чём
    -0.77
    ۞
    -0.77
    श्यक
    -0.76
    ガー
    -0.76
     terminer
    -0.76
     harmonie
    -0.76
    POSITIVE LOGITS
     faculty
    0.93
     graduate
    0.88
    Attached
    0.82
     affiliated
    0.82
     attached
    0.82
     Faculty
    0.82
     division
    0.81
     Attached
    0.77
     divisions
    0.77
     Frontier
    0.75
    Activations Density 0.024%

    No Known Activations