© 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. 44811
    Prev
    Next
    INDEX
    Explanations

    I can

    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
     itſelf
    -1.59
    蟶
    -1.49
     staffel
    -1.49
     spannend
    -1.48
     voyageurs
    -1.48
     metodología
    -1.44
     laboratorium
    -1.44
     visualización
    -1.41
     tirs
    -1.41
     verborgen
    -1.41
    POSITIVE LOGITS
    there
    1.69
     viena
    1.52
           
    1.50
        
    1.50
     lietu
    1.46
    one
    1.45
     tık
    1.43
     üzer
    1.41
     moż
    1.41
    with
    1.41
    Activations Density 0.128%

    No Known Activations