© 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. 31-GEMMASCOPE-2-RES-262K
    7. 48664
    Prev
    Next
    INDEX
    Explanations

    compensation payroll

    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_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     রামগতি
    0.47
    lipstick
    0.45
     টেলিগ্রাফ
    0.44
    aven
    0.44
    θ
    0.43
    美国
    0.42
    。
    0.41
    品牌
    0.40
    hattan
    0.40
    电视
    0.40
    POSITIVE LOGITS
     utilising
    0.45
    謎
    0.44
    ContactBundle
    0.43
     sondern
    0.41
     nemesis
    0.41
    แต่
    0.40
     despre
    0.40
     quoting
    0.40
     uprising
    0.40
     Tako
    0.39
    Activations Density 0.001%

    No Known Activations