© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 15548
    Prev
    Next
    INDEX
    Explanations

    online pharmacy and ordering healthcare

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

    file, data, photo, equation, numbers, audio

    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_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
    军事
    0.46
     cataracts
    0.43
     ٣
    0.43
     rap
    0.41
     पछ
    0.41
     znacznie
    0.40
     दुरुपयोग
    0.40
     घेण्यात
    0.40
     있었다
    0.39
    raits
    0.39
    POSITIVE LOGITS
     with
    0.54
     via
    0.52
     کنید
    0.51
     without
    0.50
     by
    0.48
     yourself
    0.47
     WITHOUT
    0.47
    至
    0.47
     используя
    0.46
    IfNeeded
    0.46
    Activations Density 0.207%

    No Known Activations