© 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. 22-GEMMASCOPE-RES-131K
    7. 66515
    Prev
    Next
    INDEX
    Explanations

    introduction of new items or replacements

    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
     finir
    -1.05
     первом
    -0.97
     rodillas
    -0.97
    PREPARATION
    -0.96
     pressured
    -0.93
     genoux
    -0.91
     disminuir
    -0.91
     kind
    -0.90
    详细信息
    -0.90
    achite
    -0.90
    POSITIVE LOGITS
     for
    1.50
     replacement
    1.18
     replacements
    1.07
     hukum
    1.07
     Replacement
    0.98
     replaces
    0.97
     replace
    0.97
    );"
    0.96
     replaced
    0.95
     after
    0.94
    Activations Density 0.061%

    No Known Activations