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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 53-GEMMASCOPE-2-RES-262K
    7. 35348
    Prev
    Next
    INDEX
    Explanations

    Disco Elysium

    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_53_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
    Brent
    0.37
     പിടി
    0.37
    一致
    0.36
    셈
    0.36
     Griffin
    0.36
     Brent
    0.36
    聘
    0.35
     Irvine
    0.35
    的小
    0.34
     Kruger
    0.34
    POSITIVE LOGITS
     Commiss
    0.43
     dulu
    0.38
    Dtls
    0.38
     COMPLEXES
    0.38
    Initializer
    0.38
    ^{+},
    0.38
    Intern
    0.37
    icklabels
    0.37
     Comm
    0.36
    Comm
    0.36
    Activations Density 0.004%

    No Known Activations