© 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-65K
    7. 28452
    Prev
    Next
    INDEX
    Explanations

    foreign language endings

    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_65k_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
     troops
    0.54
     providers
    0.52
     margin
    0.50
     prepayment
    0.50
     incontinence
    0.48
     elder
    0.47
     conservatory
    0.47
    会
    0.47
     pipelines
    0.47
    はや
    0.47
    POSITIVE LOGITS
    wanath
    0.51
    andez
    0.49
    íč
    0.47
    iz
    0.46
    zinha
    0.46
     comentário
    0.46
    ík
    0.44
    ária
    0.44
    kelijke
    0.44
    ilas
    0.44
    Activations Density 0.013%

    No Known Activations