© 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. 24890
    Prev
    Next
    INDEX
    Explanations

    un, bất, 불 and following characters

    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
    য়দ
    0.46
     gover
    0.44
    elben
    0.43
     வெளிப்புற
    0.43
    ometimes
    0.41
     popOperand
    0.41
     解析
    0.41
     гро
    0.40
    ține
    0.40
    ﹔
    0.40
    POSITIVE LOGITS
    Zam
    0.47
     pter
    0.41
    Fusion
    0.39
     불
    0.38
    ぐる
    0.38
     incom
    0.38
    Anth
    0.37
    不
    0.37
    ግ
    0.37
     grievance
    0.37
    Activations Density 0.000%

    No Known Activations