© 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. 12118
    Prev
    Next
    INDEX
    Explanations

    programming syntax and keywords

    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
    Bayes
    -0.69
    暴
    -0.66
    yā
    -0.65
     Regularly
    -0.65
     results
    -0.65
    赛
    -0.63
     kult
    -0.63
     serial
    -0.63
    FromFile
    -0.61
     Rab
    -0.61
    POSITIVE LOGITS
     couverture
    0.76
     gelap
    0.75
    Logs
    0.70
     zufolge
    0.67
     Dobbs
    0.65
    öll
    0.65
    ླ
    0.65
    DIM
    0.65
    USH
    0.64
    祝い
    0.64
    Activations Density 0.058%

    No Known Activations