© 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. 24889
    Prev
    Next
    INDEX
    Explanations

    actions repeated multiple times

    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
     использовать
    0.44
    ொள்
    0.43
    只会
    0.41
     தொகை
    0.40
     музыку
    0.39
     أكتوبر
    0.39
    חנו
    0.38
    샛
    0.38
    ピアノ
    0.38
     пропор
    0.38
    POSITIVE LOGITS
    繰り返
    0.70
     repetitions
    0.65
     repeated
    0.62
     repeat
    0.60
     repeating
    0.59
     répét
    0.59
     repetition
    0.55
     repetir
    0.55
     반복
    0.55
     repeats
    0.53
    Activations Density 0.038%

    No Known Activations