© 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. 90159
    Prev
    Next
    INDEX
    Explanations

    complementary, supplementary, and series concepts

    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
     dalje
    0.54
    য়ান
    0.54
    '
    0.54
    ඵ
    0.53
    返回
    0.53
     phosphatase
    0.50
     покрытия
    0.50
     возвра
    0.49
     напряжения
    0.48
     пато
    0.48
    POSITIVE LOGITS
    ra
    0.59
     Storia
    0.55
     História
    0.54
    g
    0.54
     hilarious
    0.52
     Histoire
    0.52
     Risiko
    0.52
    狱
    0.52
     Hindu
    0.51
     Captain
    0.50
    Activations Density 0.000%

    No Known Activations