© 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-65K
    7. 49155
    Prev
    Next
    INDEX
    Explanations

    societal aspects and historical biases

    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
     screws
    0.54
     qued
    0.48
     Navbar
    0.46
     eels
    0.45
    Г
    0.44
     (
    0.44
     machined
    0.43
     er
    0.43
     =
    0.43
     passed
    0.42
    POSITIVE LOGITS
    উল্লেখ
    0.50
    ᅩ
    0.50
    卄
    0.50
    ತಿ
    0.48
    conscious
    0.48
    τρο
    0.48
    𝐨
    0.48
     აღმასრულებელი
    0.48
     কমিশনার
    0.47
    hosting
    0.47
    Activations Density 0.003%

    No Known Activations