© 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. 34286
    Prev
    Next
    INDEX
    Explanations

    instructions following common verbs

    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
     really
    -1.11
     its
    -1.09
     putting
    -1.07
     our
    -1.05
     garagem
    -0.99
     such
    -0.98
     retten
    -0.97
     iluminação
    -0.96
     trying
    -0.94
     barato
    -0.94
    POSITIVE LOGITS
     oignon
    0.98
    issão
    0.98
     ایشان
    0.98
    präche
    0.97
    èvent
    0.95
     дори
    0.94
     آزادی
    0.93
    
    0.93
     делу
    0.93
     metic
    0.92
    Activations Density 0.059%

    No Known Activations