© 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. 104228
    Prev
    Next
    INDEX
    Explanations

    asynchronous operations using threads

    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
    Langkah
    -0.97
    Those
    -0.96
    Even
    -0.93
    Some
    -0.93
     in
    -0.92
    otriva
    -0.92
    保險
    -0.91
    Getting
    -0.90
    Things
    -0.90
    Manfaat
    -0.90
    POSITIVE LOGITS
     gier
    0.98
     OBITUARY
    0.97
    CMV
    0.96
    AtPosition
    0.94
     aconse
    0.94
    '~
    0.93
     alunos
    0.92
    mbar
    0.92
    lossing
    0.91
     tâches
    0.91
    Activations Density 0.033%

    No Known Activations