© 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-TRANSCODER-262K
    7. 9119
    Prev
    Next
    INDEX
    Explanations

    peace and peacekeeping

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_width_262k_l0_small_affine
    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
     சரும
    0.43
     stockings
    0.42
     व्यंजन
    0.39
     bugs
    0.38
     Bugs
    0.38
     lures
    0.37
     medication
    0.36
    鬏
    0.36
     excels
    0.35
    橱
    0.35
    POSITIVE LOGITS
     peace
    1.30
    peace
    1.20
     Peace
    1.13
    Peace
    1.12
    和平
    1.05
     peac
    1.02
     PEACE
    0.99
     শান্তি
    0.97
     paz
    0.95
     peacekeeping
    0.90
    Activations Density 0.065%

    No Known Activations