© 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. 88018
    Prev
    Next
    INDEX
    Explanations

    Wed Apr

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

    coding and specific terms

    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
     برانيه
    0.51
    </h2>
    0.47
    TRIGGER
    0.46
    公寓
    0.46
    酒店
    0.45
    ্ল
    0.44
    二
    0.43
    事務
    0.43
    オフィス
    0.43
    王子
    0.41
    POSITIVE LOGITS
     ถ้า
    0.49
     गोइंग
    0.48
    จะไม่
    0.48
     เดิน
    0.48
     Иногда
    0.47
     เข้า
    0.46
     यूँ
    0.46
     मोल
    0.46
     negotiations
    0.45
     плю
    0.45
    Activations Density 0.001%

    No Known Activations