© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 221720
    Prev
    Next
    INDEX
    Explanations

    lock free and multi-producer multi-consumer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    把我
    0.43
     intracellular
    0.39
    蹩
    0.38
     meetings
    0.37
     mejoras
    0.37
     sailors
    0.37
     unproductive
    0.37
     denitrification
    0.36
     Anzahl
    0.36
    广播
    0.36
    POSITIVE LOGITS
     奥
    0.42
     brighter
    0.41
    奧
    0.40
     Ó
    0.39
     تۆ
    0.39
    ˆ
    0.39
    োরে
    0.38
     cung
    0.38
     Calf
    0.38
    Њ
    0.38
    Activations Density 0.001%

    No Known Activations