© 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-16K
    7. 12634
    Prev
    Next
    INDEX
    Explanations

    name followed by double underscore

    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_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     __
    0.62
    __,
    0.52
    __
    0.46
    .__
    0.45
    __)
    0.43
     ireo
    0.42
    ꞌ
    0.41
    Demo
    0.39
    ___
    0.38
     "__
    0.38
    POSITIVE LOGITS
     treatment
    0.44
    țial
    0.42
    ທ່ານ
    0.41
     치료
    0.41
    治疗
    0.40
     replacement
    0.40
     distraction
    0.39
     cruelty
    0.39
     avoid
    0.39
    HeaderText
    0.39
    Activations Density 0.008%

    No Known Activations