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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 40213
    Prev
    Next
    INDEX
    Explanations

    context around specific words

    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
    Not in Any Lists

    No Comments

    Negative Logits
     militaires
    0.45
    ਵ
    0.45
     pertaining
    0.43
     appendages
    0.43
     subordination
    0.42
    neho
    0.42
    нную
    0.42
    ielles
    0.42
     pursuits
    0.42
    隙
    0.42
    POSITIVE LOGITS
     Irina
    0.45
     Fellow
    0.43
    you
    0.41
    Tickets
    0.41
     Daisy
    0.40
     Caroline
    0.40
     Revised
    0.40
    Festival
    0.40
    大力
    0.39
    人家
    0.39
    Activations Density 0.002%

    No Known Activations