© 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. 34716
    Prev
    Next
    INDEX
    Explanations

    career and fields of interest

    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
     FISHING
    -1.02
    🐡
    -1.01
     situatie
    -1.00
    oudoune
    -0.98
     ordina
    -0.97
     проживания
    -0.97
     existant
    -0.96
     activités
    -0.95
    Напомним
    -0.95
     acide
    -0.94
    POSITIVE LOGITS
     combine
    1.36
     field
    1.21
     Combine
    1.12
     working
    1.11
     fields
    1.10
     helping
    1.07
    Combine
    1.04
     jobs
    1.00
     my
    1.00
     pursue
    0.97
    Activations Density 0.036%

    No Known Activations