© 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. 65421
    Prev
    Next
    INDEX
    Explanations

    public domain, licenses, copyright

    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
    unoz
    -0.81
     attributed
    -0.80
     Fair
    -0.79
     impianti
    -0.79
     governing
    -0.78
     Beton
    -0.77
     sinta
    -0.75
     welcomed
    -0.75
     锁
    -0.74
     ®
    -0.73
    POSITIVE LOGITS
     International
    0.91
    rógeno
    0.85
     international
    0.80
    bilir
    0.79
    International
    0.75
     preoperative
    0.75
    łog
    0.74
     Inhalten
    0.74
    Humble
    0.74
    Judi
    0.73
    Activations Density 0.058%

    No Known Activations