© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 106562
    Prev
    Next
    INDEX
    Explanations

    university schools and deans

    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
     COLLEGE
    -0.85
    ")[
    -0.84
     College
    -0.84
    več
    -0.80
    チェーン
    -0.78
    ใส
    -0.77
     aurez
    -0.76
    されており
    -0.74
    тельства
    -0.74
    大学の
    -0.72
    POSITIVE LOGITS
     Dean
    1.30
     dean
    1.20
    Dean
    1.20
     DEAN
    0.97
    roffen
    0.88
    informatics
    0.85
    Chico
    0.81
    Belize
    0.79
    progressbar
    0.79
     departments
    0.79
    Activations Density 0.037%

    No Known Activations