© 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. 22424
    Prev
    Next
    INDEX
    Explanations

    here followed by I or we

    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
     is
    -2.27
     should
    -2.00
     would
    -2.00
     has
    -1.77
     could
    -1.63
    ↵
    -1.59
     badkamer
    -1.52
     of
    -1.48
     use
    -1.48
     she
    -1.47
    POSITIVE LOGITS
    gerichte
    1.45
    
    1.43
     demokra
    1.41
     enthou
    1.37
     mengen
    1.37
    蓐
    1.35
     liquide
    1.33
    ꪹ
    1.33
     deras
    1.32
    
    1.32
    Activations Density 0.017%

    No Known Activations