© 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. 40-GEMMASCOPE-2-RES-16K
    7. 9027
    Prev
    Next
    INDEX
    Explanations

    I followed by past tense auxiliary

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

    auxiliary verbs indicating state or past action

    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_40_width_16k_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
    න්නේ
    0.55
     बोलेंगे
    0.52
    なくなる
    0.49
     बनेगा
    0.48
     গেলাম
    0.48
     வழங்கப்படும்
    0.48
     बनेंगे
    0.48
     রই
    0.47
    هي
    0.47
     করব
    0.45
    POSITIVE LOGITS
     telah
    2.77
     đã
    2.13
     has
    1.95
     হয়েছে
    1.85
     হয়েছে
    1.78
     করেছেন
    1.75
     heeft
    1.72
     করেছে
    1.67
     olmuş
    1.64
    িয়েছে
    1.62
    Activations Density 2.267%

    No Known Activations