© 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-262K
    7. 137636
    Prev
    Next
    INDEX
    Explanations

    defining core concepts

    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_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     finals
    0.43
     গ্রন্থ
    0.40
     punishing
    0.39
     Dislocations
    0.39
     weakening
    0.38
    onResume
    0.38
     Michaelmas
    0.37
     cropping
    0.37
    ዞ
    0.37
     yake
    0.37
    POSITIVE LOGITS
    algorithms
    0.40
    efully
    0.39
    공
    0.39
    Ком
    0.38
    снов
    0.38
    iren
    0.38
    기술
    0.38
    cee
    0.37
    
    0.36
    টিয়ে
    0.35
    Activations Density 0.000%

    No Known Activations