© 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-65K
    7. 56232
    Prev
    Next
    INDEX
    Explanations

    Subject: lines

    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_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ण्यास
    0.40
    放到
    0.40
    ให้กับ
    0.40
     kepada
    0.40
    到
    0.38
     किससे
    0.38
    㸸
    0.37
     টু
    0.37
     తమ
    0.36
    environments
    0.36
    POSITIVE LOGITS
     الصفحة
    0.43
    third
    0.42
     página
    0.41
     pages
    0.40
    meni
    0.39
     plead
    0.38
     BSE
    0.38
    ედ
    0.38
    copied
    0.38
     pleaded
    0.37
    Activations Density 0.006%

    No Known Activations