© 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. 31-GEMMASCOPE-2-RES-65K
    7. 31492
    Prev
    Next
    INDEX
    Explanations

    fired, cost, archaeological, intends

    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_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     yourself
    0.48
     endroits
    0.46
     oftentimes
    0.45
    </u>
    0.41
    utes
    0.40
     tripped
    0.39
     الاجابه
    0.39
    ot
    0.38
    upo
    0.38
    बा
    0.38
    POSITIVE LOGITS
    TotalPrice
    0.51
     Contract
    0.47
    🧩
    0.47
    🤍
    0.45
     Electrochemical
    0.45
    🥸
    0.45
     blackmail
    0.44
    認証
    0.43
     پرداخت
    0.43
    💶
    0.42
    Activations Density 0.033%

    No Known Activations