© 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. 40-GEMMASCOPE-2-RES-262K
    7. 2925
    Prev
    Next
    INDEX
    Explanations

    handle, cholesterol, azure

    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_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ים
    0.41
     Indy
    0.40
    e
    0.40
    解锁
    0.39
    ляться
    0.39
    amata
    0.39
    াল
    0.38
    rset
    0.38
    aboo
    0.38
     fulfillment
    0.38
    POSITIVE LOGITS
     quelquefois
    0.47
     oftentimes
    0.47
    Variables
    0.47
    葶
    0.46
    저는
    0.46
    ኼ
    0.46
    ឬ
    0.45
    ippings
    0.45
     భ
    0.43
     定义
    0.43
    Activations Density 0.000%

    No Known Activations