© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 3084
    Prev
    Next
    INDEX
    Explanations

    today

    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_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     on
    0.70
     বলেছিল
    0.56
     congel
    0.55
    的時間
    0.54
    )。
    0.54
     hurriedly
    0.54
     ambush
    0.54
     looming
    0.53
     previamente
    0.53
    </h3>
    0.52
    POSITIVE LOGITS
    today
    0.98
    今日
    0.98
     oggi
    0.95
     TODAY
    0.95
     आज
    0.93
     сегодня
    0.89
     today
    0.87
     сьогодні
    0.87
     Today
    0.84
     hôm
    0.81
    Activations Density 0.022%

    No Known Activations