© 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. 58559
    Prev
    Next
    INDEX
    Explanations

    Hong Kong

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

    writing in Chinese

    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
     furo
    0.49
     tens
    0.47
     อะไร
    0.47
     ਹੋ
    0.47
     フェ
    0.46
     ent
    0.46
    —
    0.46
     quinze
    0.45
     agonizing
    0.45
     padd
    0.45
    POSITIVE LOGITS
    妆
    0.57
    妝
    0.55
    اء
    0.48
    اع
    0.48
    ının
    0.47
    传染
    0.47
    长沙
    0.46
    德
    0.45
    胜
    0.45
    桥
    0.45
    Activations Density 0.000%

    No Known Activations