© 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. 22-GEMMASCOPE-RES-131K
    4. 95637
    Prev
    Next
    INDEX
    Explanations

    checking answers

    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_22/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
     kraft
    -0.94
    ById
    -0.88
    gné
    -0.88
     conflits
    -0.87
     spesial
    -0.86
     сумка
    -0.85
    ୨
    -0.82
     recommande
    -0.81
    üy
    -0.81
     distanciation
    -0.80
    POSITIVE LOGITS
     correct
    1.21
     answers
    1.20
     either
    1.20
     answer
    1.17
     любы
    1.06
     students
    0.98
     correcta
    0.98
     podían
    0.94
     Answers
    0.94
    ssens
    0.94
    Activations Density 0.049%

    No Known Activations