© 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. 10-GEMMASCOPE-RES-131K
    7. 41588
    Prev
    Next
    INDEX
    Explanations

    options assignment or parameter

    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_10/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
     that
    -2.05
     those
    -1.73
     Reſ
    -1.68
    我们在
    -1.68
     and
    -1.60
    ;}
    -1.55
     atunci
    -1.53
     Inſ
    -1.52
    </b>
    -1.49
     through
    -1.49
    POSITIVE LOGITS
    
    2.08
    
    2.00
    ☫
    1.94
    
    1.91
    𖡼
    1.86
    動か
    1.84
    〠
    1.83
     universitarios
    1.82
     robuste
    1.81
     judíos
    1.81
    Activations Density 0.035%

    No Known Activations