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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 4830
    Prev
    Next
    INDEX
    Explanations

    companies from

    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
    єї
    0.49
    с
    0.47
    шина
    0.46
     oyn
    0.46
    ли
    0.46
    ूर
    0.46
    的声音
    0.45
    鍔
    0.43
    тря
    0.42
     dịch
    0.42
    POSITIVE LOGITS
     valuations
    0.51
     monasteries
    0.47
     asignar
    0.45
     পাচ্ছি
    0.45
    aciones
    0.43
     activations
    0.43
    álního
    0.41
     Logos
    0.41
     advent
    0.41
     ابر
    0.41
    Activations Density 0.020%

    No Known Activations