© 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. 106523
    Prev
    Next
    INDEX
    Explanations

    Musk, circle distance

    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
    worth
    0.70
    à
    0.69
    is
    0.67
    will
    0.67
     နောက်
    0.66
    with
    0.65
     Một
    0.64
    é
    0.63
    owns
    0.62
    creates
    0.62
    POSITIVE LOGITS
    我们
    0.57
    峡
    0.53
    توى
    0.53
    ט
    0.53
    边
    0.51
    类别
    0.51
    基础上
    0.50
    科学家
    0.50
    严
    0.50
    可以
    0.49
    Activations Density 0.000%

    No Known Activations