© 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. 93858
    Prev
    Next
    INDEX
    Explanations

    http URLs

    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
     our
    -1.25
     出版
    -0.94
     cometer
    -0.90
    そして
    -0.85
     ONLY
    -0.84
     fotbal
    -0.84
    ducati
    -0.84
     بيها
    -0.84
    (*´
    -0.82
    teamId
    -0.82
    POSITIVE LOGITS
     http
    2.36
    http
    2.33
     www
    1.90
    www
    1.88
     URL
    1.84
    URL
    1.69
     url
    1.47
     URLs
    1.41
     available
    1.41
    available
    1.38
    Activations Density 0.060%

    No Known Activations