© 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. 22-GEMMASCOPE-RES-131K
    7. 129388
    Prev
    Next
    INDEX
    Explanations

    positions and affiliations

    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_22/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
     UITextField
    -1.31
     MyBatis
    -1.31
    
    -1.28
     testen
    -1.27
     traiter
    -1.23
     icônes
    -1.22
     avantages
    -1.22
     fonctionnalités
    -1.20
     remercier
    -1.20
    
    -1.20
    POSITIVE LOGITS
     community
    1.43
     As
    1.28
     Women
    1.27
     two
    1.27
     some
    1.27
     several
    1.26
     people
    1.24
     numerous
    1.24
     at
    1.23
     There
    1.22
    Activations Density 0.020%

    No Known Activations