© 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-262K
    7. 7726
    Prev
    Next
    INDEX
    Explanations

    your/you in different languages

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron detects major document structure—section headers and the starts of long, high-level assistant responses (i.e., prominent section intros).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
     उसने
    0.36
    मैंने
    0.34
    were
    0.29
     उन्होंने
    0.29
     mesi
    0.29
     তুলেছে
    0.29
     hubo
    0.29
     putative
    0.28
     requested
    0.28
    该公司
    0.28
    POSITIVE LOGITS
    あなたの
    0.44
    your
    0.41
     നിങ്ങളുടെ
    0.41
     あなた
    0.40
     আপনার
    0.39
     your
    0.38
     ваш
    0.38
     bạn
    0.38
    Getting
    0.38
     તમારા
    0.37
    Activations Density 0.256%

    No Known Activations