© 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. 59127
    Prev
    Next
    INDEX
    Explanations

    colleges, schools, and faculties

    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
     فرزند
    -0.73
     君
    -0.73
    unciation
    -0.73
     eventuell
    -0.73
     Termination
    -0.72
    iestety
    -0.71
     Fractional
    -0.70
    クリス
    -0.69
    lid
    -0.69
    termination
    -0.69
    POSITIVE LOGITS
     School
    2.81
    School
    2.25
     College
    2.05
     SCHOOL
    1.77
     Schools
    1.77
    SCHOOL
    1.73
     school
    1.70
     Faculty
    1.66
     schools
    1.58
    College
    1.58
    Activations Density 0.081%

    No Known Activations