© 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-16K
    7. 12338
    Prev
    Next
    INDEX
    Explanations

    end else

    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_16k_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
    𝑐
    0.38
    Rồi
    0.36
    ቮ
    0.36
    addGap
    0.35
    ثل
    0.35
    ኣ
    0.35
    やはり
    0.34
     や
    0.33
     számos
    0.33
     برضو
    0.33
    POSITIVE LOGITS
     else
    3.00
    else
    2.69
     otherwise
    2.61
     Else
    2.53
     Otherwise
    2.39
    Otherwise
    2.33
    否则
    2.28
    otherwise
    2.23
    Else
    2.20
     sonst
    2.20
    Activations Density 0.118%

    No Known Activations