© 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. 90926
    Prev
    Next
    INDEX
    Explanations

    occupation, pause, finish

    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
     to
    -1.26
     which
    -1.23
    ;
    -1.20
     who
    -1.04
     so
    -0.89
     and
    -0.89
     ;
    -0.88
    mamp
    -0.88
     plus
    -0.86
    composición
    -0.85
    POSITIVE LOGITS
     interrom
    1.16
     occuper
    1.14
     plafon
    1.11
    yarnpkg
    1.11
     pantalon
    1.11
     restant
    1.07
    >,</
    1.05
     autonomie
    1.05
    IMENTS
    1.00
     fermer
    1.00
    Activations Density 0.001%

    No Known Activations