© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 1824
    Prev
    Next
    INDEX
    Explanations

    properties and definitions

    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_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
    ！！
    0.49
     Tapatalk
    0.44
     waivers
    0.43
    ！
    0.43
     Caves
    0.40
     সমঝো
    0.39
     Peaks
    0.39
     Blush
    0.39
     Hostel
    0.38
     التواصل
    0.38
    POSITIVE LOGITS
    rische
    0.50
    ritt
    0.46
    ries
    0.44
    st
    0.44
    ctions
    0.43
     kund
    0.43
    ég
    0.43
    г
    0.43
    expl
    0.42
     ട
    0.42
    Activations Density 0.011%

    No Known Activations