© 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. 89448
    Prev
    Next
    INDEX
    Explanations

    Hualien (花蓮), SSH keys

    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
    t
    1.37
    el
    1.02
    ed
    0.97
    ine
    0.96
    the
    0.90
     The
    0.89
    ت
    0.82
    0
    0.80
    ten
    0.79
    ing
    0.77
    POSITIVE LOGITS
    לי
    0.76
    ني
    0.72
    的には
    0.70
    直線
    0.70
    ני
    0.69
    前に
    0.68
    רי
    0.67
    この記事
    0.67
    そして
    0.67
    すぐに
    0.66
    Activations Density 0.002%

    No Known Activations