© 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. 60827
    Prev
    Next
    INDEX
    Explanations

    http links and non-english

    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
     while
    -0.95
    ✍
    -0.95
     kvad
    -0.93
    </>
    -0.91
    *</
    -0.90
     pude
    -0.89
     idiota
    -0.88
    writeFileSync
    -0.87
     versión
    -0.86
    -</
    -0.85
    POSITIVE LOGITS
     fiecare
    0.96
     ameste
    0.92
    ご連絡
    0.91
     прошло
    0.90
     디
    0.87
     isole
    0.85
     surpasses
    0.84
    radiated
    0.84
     udě
    0.82
     urma
    0.82
    Activations Density 0.011%

    No Known Activations