© 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. 192028
    Prev
    Next
    INDEX
    Explanations

    can vary or differ

    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
    midt
    0.45
    遏
    0.41
    完整的
    0.40
     letzte
    0.40
     Schre
    0.39
     Draft
    0.39
     respectable
    0.38
    鏝
    0.38
    neider
    0.38
     scén
    0.37
    POSITIVE LOGITS
    튜브
    0.40
    तरा
    0.38
     tareas
    0.38
    খর
    0.38
     tempted
    0.38
    आगे
    0.38
    хие
    0.38
     selfies
    0.37
    早速
    0.37
    due
    0.36
    Activations Density 0.000%

    No Known Activations