© 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. 76485
    Prev
    Next
    INDEX
    Explanations

    formal language L

    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
    OfWork
    -0.76
    Spreadsheet
    -0.73
     Vieira
    -0.72
    крови
    -0.71
     ország
    -0.70
     chips
    -0.68
    пин
    -0.68
     мебель
    -0.66
     spoiling
    -0.66
     vineyards
    -0.66
    POSITIVE LOGITS
     Epsilon
    1.25
     language
    1.23
    epsilon
    1.19
     Language
    1.19
     ε
    1.19
    Epsilon
    1.14
     closure
    1.11
     epsilon
    1.11
    closure
    1.07
    language
    1.00
    Activations Density 0.034%

    No Known Activations