© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 39517
    Prev
    Next
    INDEX
    Explanations

    HERE location or link

    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
    ྥ
    -1.86
     réalisée
    -1.80
     annuelle
    -1.79
     Также
    -1.77
    蟶
    -1.76
     actuelles
    -1.74
     Поэтому
    -1.70
     We
    -1.70
    >
    -1.70
     extérieures
    -1.66
    POSITIVE LOGITS
     "
    2.17
     sokak
    2.09
     we
    2.05
     HERE
    2.03
    
    1.89
     pimienta
    1.88
    횃
    1.84
    ſelf
    1.80
    
    1.80
     significado
    1.78
    Activations Density 0.003%

    No Known Activations