© 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. 56738
    Prev
    Next
    INDEX
    Explanations

    modes, filters, or processes

    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
     robberies
    0.46
     குறைந்த
    0.43
     shoppers
    0.38
     cashback
    0.38
     shopper
    0.38
    ングラス
    0.38
     discut
    0.37
     qubit
    0.37
    </tr>
    0.37
     cercanos
    0.37
    POSITIVE LOGITS
    fell
    0.40
    Mods
    0.40
    ISAM
    0.39
     ෆ
    0.39
     шы
    0.39
    袠
    0.39
     أعمال
    0.39
    ΑΣ
    0.38
     refe
    0.38
     Ammonium
    0.38
    Activations Density 0.008%

    No Known Activations