© 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. 16-GEMMASCOPE-2-RES-262K
    7. 48180
    Prev
    Next
    INDEX
    Explanations

    fit for purpose

    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
     a
    1.00
    ،
    0.87
     в
    0.80
     d
    0.79
    www
    0.74
     be
    0.71
     D
    0.69
     د
    0.68
    r
    0.67
     مسلسل
    0.66
    POSITIVE LOGITS
    ע
    1.00
    지
    1.00
     fabriqu
    0.87
    at
    0.85
    ката
    0.85
    คุณ
    0.84
     aplatis
    0.83
    ल
    0.83
    ból
    0.81
    ক
    0.81
    Activations Density 0.000%

    No Known Activations