© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 75530
    Prev
    Next
    INDEX
    Explanations

    honorary and hereditary titles

    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
    \
    -3.45
     Для
    -2.42
     When
    -2.42
     OF
    -2.41
     أو
    -2.39
     "",
    -2.28
     In
    -2.19
     The
    -2.16
    	
    -2.09
     où
    -2.09
    POSITIVE LOGITS
    </sup>
    2.73
    
    2.41
      -
    2.41
    </h2>
    2.30
    $
    2.30
     sinistro
    2.28
     bianco
    2.25
     visse
    2.20
     untuk
    2.19
     esat
    2.17
    Activations Density 0.003%

    No Known Activations