© 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. 23597
    Prev
    Next
    INDEX
    Explanations

    k, k, K, spelling, kodi, kürze

    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
    有所
    0.39
    /∂
    0.39
    ought
    0.38
     사용하는
    0.35
     počas
    0.35
    đa
    0.35
    Mâc
    0.35
    ∪
    0.35
    valor
    0.35
    鯉
    0.35
    POSITIVE LOGITS
    ױ
    0.42
    ূট
    0.42
    ह्न
    0.42
     boy
    0.40
     क्लाइ
    0.40
    Head
    0.39
    uft
    0.38
     kürz
    0.38
    schaft
    0.38
     kämp
    0.38
    Activations Density 0.001%

    No Known Activations