© 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. 215667
    Prev
    Next
    INDEX
    Explanations

    IRS, validated, determined

    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
     Эк
    0.39
    ibh
    0.38
     Display
    0.37
    యి
    0.36
    Lug
    0.36
     Horror
    0.36
    ധാന
    0.36
    柰
    0.36
     Hair
    0.35
     Champion
    0.35
    POSITIVE LOGITS
     trainee
    0.39
    ジェ
    0.39
     visão
    0.37
     wellbeing
    0.37
     gaz
    0.36
     quartet
    0.34
    setView
    0.34
    散
    0.34
     வெளிப்புற
    0.33
    一旦
    0.33
    Activations Density 0.001%

    No Known Activations