© 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-262K
    7. 129298
    Prev
    Next
    INDEX
    Explanations

    already been deallocated

    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_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    يارات
    0.50
     controladores
    0.48
    t
    0.47
     responsables
    0.45
    त्रेयी
    0.45
    elwv
    0.45
    莆
    0.45
    مس
    0.43
    คโน
    0.43
     utilisant
    0.42
    POSITIVE LOGITS
     물론
    0.49
     هم
    0.44
     하지만
    0.44
     ან
    0.43
     شکل
    0.43
    TPS
    0.42
    ந்துள்ளது
    0.42
     ویت
    0.42
     Sudah
    0.42
     همین
    0.41
    Activations Density 0.000%

    No Known Activations