© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 194742
    Prev
    Next
    INDEX
    Explanations

    human relationships and plans

    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
    Not in Any Lists

    No Comments

    Negative Logits
     আবদুল
    0.38
     curd
    0.38
     Huo
    0.37
     fi
    0.36
     demonstrate
    0.36
     Zhang
    0.36
    wold
    0.36
     建
    0.36
     stru
    0.35
     Đồng
    0.35
    POSITIVE LOGITS
    人間の
    0.48
     البشر
    0.46
    anthrop
    0.46
     انسانی
    0.45
    Human
    0.43
     Anthrop
    0.42
    QUALITY
    0.42
    スク
    0.41
    Hero
    0.41
    Impossible
    0.41
    Activations Density 0.001%

    No Known Activations