© 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. 40979
    Prev
    Next
    INDEX
    Explanations

    Here's a breakdown:

    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
    Not in Any Lists

    No Comments

    Negative Logits
    或者
    0.40
    そも
    0.38
     pourront
    0.37
     hao
    0.37
    打印
    0.36
     শরীরের
    0.35
     অথবা
    0.35
    祹
    0.34
    或者是
    0.34
    显示的
    0.33
    POSITIVE LOGITS
     terrib
    0.46
     brzo
    0.46
     drei
    0.46
     recente
    0.42
     recentes
    0.42
     ominous
    0.41
     अपेक्षा
    0.40
     reciente
    0.39
     எளி
    0.39
     aici
    0.38
    Activations Density 0.075%

    No Known Activations