© 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. 130066
    Prev
    Next
    INDEX
    Explanations

    design, context

    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
     skiers
    0.39
     defenders
    0.37
     insurers
    0.37
     قائمة
    0.36
    נד
    0.36
    integrated
    0.35
     deliberations
    0.35
    
    0.35
     offenders
    0.35
    ʏ
    0.34
    POSITIVE LOGITS
    ority
    0.50
     brady
    0.41
     metri
    0.40
     misleading
    0.40
     赵
    0.39
    !..
    0.39
    ubility
    0.38
     spout
    0.38
    xygen
    0.38
     myth
    0.38
    Activations Density 0.000%

    No Known Activations