© 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. 120436
    Prev
    Next
    INDEX
    Explanations

    shopping cart, chosen drug, social media

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

    eating contests

    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
    组成
    0.43
    ول
    0.42
    商
    0.42
    懋
    0.41
     কমিউনিস্ট
    0.41
    污染
    0.41
    工作中
    0.40
    剑
    0.40
    ร
    0.38
    linge
    0.38
    POSITIVE LOGITS
     región
    0.54
    ವಿದೆ
    0.54
     debilit
    0.50
     отличается
    0.49
     deberán
    0.47
     हारे
    0.47
     кома
    0.46
     sprouts
    0.46
     retires
    0.46
    ಎಸ್
    0.46
    Activations Density 0.001%

    No Known Activations