© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 9411
    Prev
    Next
    INDEX
    Explanations

    lecture numbering or sections

    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_31_width_65k_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
     Prentice
    0.37
    🎗
    0.36
    ॰
    0.34
    仂
    0.34
     গ্রন্
    0.34
    Rah
    0.34
    Something
    0.34
     Hase
    0.34
    xgb
    0.33
    峹
    0.33
    POSITIVE LOGITS
     único
    0.40
     moins
    0.40
     cares
    0.39
     நடைபெற்ற
    0.39
     unmittelbar
    0.39
     rival
    0.38
     کم
    0.38
    ţin
    0.38
     konkuren
    0.38
     непосредственно
    0.37
    Activations Density 0.005%

    No Known Activations