© 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. 31-GEMMASCOPE-2-RES-16K
    7. 5690
    Prev
    Next
    INDEX
    Explanations

    book titles and descriptions

    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_31_width_16k_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
     फिल्में
    0.64
     영화
    0.63
     фильме
    0.62
     фильм
    0.60
     фильма
    0.59
    ﭜ
    0.57
     फिल्म
    0.57
     फिल्मों
    0.57
     фильмов
    0.57
    🎥
    0.57
    POSITIVE LOGITS
    s
    0.59
    0
    0.58
    are
    0.56
     to
    0.55
    is
    0.54
    2
    0.54
     non
    0.52
    1
    0.51
    res
    0.51
    .
    0.50
    Activations Density 0.025%

    No Known Activations