© 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. 16-GEMMASCOPE-2-RES-262K
    7. 2426
    Prev
    Next
    INDEX
    Explanations

    text input fields

    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_16_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
    ä
    0.68
    of
    0.67
    Л
    0.66
     of
    0.66
    1
    0.65
    А
    0.64
     to
    0.61
    Я
    0.61
    к
    0.60
    Насе
    0.60
    POSITIVE LOGITS
     textarea
    0.65
    㴼
    0.64
     rédaction
    0.64
     textArea
    0.63
    লেখ
    0.61
     ভাষা
    0.60
     océano
    0.59
     เคย
    0.58
     bulunduğu
    0.58
     洋
    0.57
    Activations Density 0.042%

    No Known Activations