© 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. 41-GEMMASCOPE-2-RES-262K
    7. 31959
    Prev
    Next
    INDEX
    Explanations

    grilles, preconstruction, square root

    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_all/layer_41_width_262k_l0_big
    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
     четыре
    0.40
     মাটি
    0.40
     ಅಂಗ
    0.39
    icing
    0.39
     قنات
    0.39
     गुंत
    0.38
     beslut
    0.37
    驀
    0.37
    資産
    0.36
     стратегия
    0.36
    POSITIVE LOGITS
     non
    0.42
    ToServer
    0.39
     mondo
    0.39
     World
    0.39
    Republic
    0.38
    非
    0.38
    World
    0.37
    zię
    0.37
    どんどん
    0.36
    Έ
    0.36
    Activations Density 0.032%

    No Known Activations