© 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. 12995
    Prev
    Next
    INDEX
    Explanations

    website address

    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
     Pens
    0.51
    Pens
    0.42
     pens
    0.40
    iation
    0.39
    കസ
    0.39
     Paths
    0.39
    圄
    0.37
     Venue
    0.37
    getOutputStream
    0.37
     फुल
    0.37
    POSITIVE LOGITS
     strán
    0.47
    сторінку
    0.46
    isodes
    0.44
    தள
    0.41
    忄
    0.41
    page
    0.40
    sticker
    0.40
     страницу
    0.40
    страницу
    0.40
    聰
    0.39
    Activations Density 0.011%

    No Known Activations