© 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. 84261
    Prev
    Next
    INDEX
    Explanations

    contextualized quotes using xe2x80x9c and xe2x80x9d

    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
    -1.92
     -
    -1.92
    E
    -1.88
    Generally
    -1.85
    Even
    -1.85
     cuando
    -1.85
    
    -1.84
     +
    -1.80
    s
    -1.78
    Usually
    -1.75
    POSITIVE LOGITS
    
    2.19
     profils
    2.14
    2.13
    撄
    1.94
     bril
    1.92
    
    1.90
    锨
    1.90
    ajouter
    1.90
     batterie
    1.86
     zove
    1.86
    Activations Density 0.007%

    No Known Activations