© 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. 7801
    Prev
    Next
    INDEX
    Explanations

    D option labels

    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
     następnie
    -1.70
     bedeckt
    -1.55
     then
    -1.46
     begrenzt
    -1.45
     $^{
    -1.41
     erweitert
    -1.38
     όπου
    -1.35
    N
    -1.35
     two
    -1.35
     not
    -1.35
    POSITIVE LOGITS
    ’
    1.70
    
    1.66
    ⁉
    1.47
    壜
    1.45
     Fichier
    1.41
     lavable
    1.41
    啭
    1.40
     ajustable
    1.38
     lances
    1.36
     provecho
    1.34
    Activations Density 0.057%

    No Known Activations