© 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. 66002
    Prev
    Next
    INDEX
    Explanations

    code syntax and abbreviations

    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
     dată
    -0.80
    Dě
    -0.80
     蓋
    -0.79
    ա
    -0.79
     dlouho
    -0.77
    Når
    -0.77
    agung
    -0.77
     intrigued
    -0.76
    euw
    -0.76
    phylococcus
    -0.75
    POSITIVE LOGITS
     N
    0.85
     channels
    0.84
     iterations
    0.81
    щему
    0.80
     num
    0.80
    делы
    0.79
     officinalis
    0.78
     width
    0.78
     ந
    0.77
     ně
    0.76
    Activations Density 0.009%

    No Known Activations