© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 6631
    Prev
    Next
    INDEX
    Explanations

    modal verbs and 'always'

    np_acts-logits-general · gemini-2.5-flash-lite

    you can do

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vaccines
    0.41
    Flights
    0.41
     watchers
    0.39
    되
    0.39
     constituencies
    0.39
     কেন্দ্রে
    0.38
     थे
    0.38
     wellness
    0.38
    ütte
    0.38
    滘
    0.37
    POSITIVE LOGITS
     tanda
    0.43
     Kennt
    0.43
     اگر
    0.39
    robi
    0.39
    
    0.39
     දැන
    0.39
     devo
    0.39
     پہلی
    0.38
     alerta
    0.38
     lika
    0.38
    Activations Density 0.001%

    No Known Activations