© 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. 34968
    Prev
    Next
    INDEX
    Explanations

    extracting information

    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
     quartos
    -1.05
    crimin
    -1.02
     tribun
    -1.01
    OrWhiteSpace
    -0.98
     greco
    -0.98
    ;
    -0.96
     altra
    -0.94
     implementa
    -0.94
    鯪
    -0.94
     infan
    -0.93
    POSITIVE LOGITS
     extract
    1.89
     Extract
    1.81
     extracting
    1.77
     extraction
    1.59
    extract
    1.54
     from
    1.49
     Extraction
    1.45
    EXTR
    1.43
    Extract
    1.41
     Extracts
    1.34
    Activations Density 0.041%

    No Known Activations