© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 60905
    Prev
    Next
    INDEX
    Explanations

    in school

    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
     nyt
    -0.90
     PROBLE
    -0.85
     interieur
    -0.83
     vru
    -0.83
     noten
    -0.81
     eier
    -0.79
    Ź
    -0.79
     ο
    -0.77
     årets
    -0.77
     malen
    -0.77
    POSITIVE LOGITS
     college
    4.59
     university
    3.23
    college
    3.17
     school
    2.63
    College
    2.45
     College
    2.41
     seminary
    2.36
     COLLEGE
    2.36
     highschool
    2.25
     elementary
    2.19
    Activations Density 0.092%

    No Known Activations