© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 35663
    Prev
    Next
    INDEX
    Explanations

    destination information infer

    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
    시키는
    0.54
     겨
    0.51
     invoices
    0.50
    ije
    0.47
     invoice
    0.46
     평가
    0.46
     рассказать
    0.46
    ilus
    0.45
     advices
    0.45
     보고
    0.44
    POSITIVE LOGITS
     Wirtschaft
    0.46
     socioeconomic
    0.46
     Socio
    0.45
     Liebig
    0.43
    滔
    0.42
     Departament
    0.41
    号
    0.41
     appartamento
    0.41
    ҳо
    0.41
    зка
    0.41
    Activations Density 0.002%

    No Known Activations