© 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
    2. Gemma-3-27B
    3. 40-GEMMASCOPE-2-RES-16K
    4. 11798
    Prev
    Next
    INDEX
    Explanations

    government documents

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

    National Institute on Drug Abuse

    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
    弟子
    0.44
    蘅
    0.43
     drawRight
    0.42
    峄
    0.41
     ব্যার
    0.40
     kubb
    0.40
    聩
    0.39
    িৎ
    0.38
    тала
    0.38
    允许
    0.38
    POSITIVE LOGITS
     Congress
    0.53
    bellion
    0.48
     Government
    0.48
     काँग्रेस
    0.48
     CONGRESS
    0.48
    Congress
    0.47
    olan
    0.47
    congress
    0.46
    United
    0.45
    includegraphics
    0.44
    Activations Density 0.081%

    No Known Activations