© 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. 131817
    Prev
    Next
    INDEX
    Explanations

    Lucene, column structure

    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
    aktadır
    0.41
    Кра
    0.41
    兰
    0.39
    かります
    0.39
     DENUMIRE
    0.39
    謀
    0.39
     đảng
    0.38
    ありがとう
    0.38
    很
    0.38
     происходит
    0.37
    POSITIVE LOGITS
     Emperor
    0.43
     hydro
    0.41
     laps
    0.39
     March
    0.38
     maju
    0.38
    immune
    0.37
     emperor
    0.37
     Empress
    0.37
     feared
    0.36
     fracture
    0.36
    Activations Density 0.000%

    No Known Activations