© 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. 40-GEMMASCOPE-2-RES-262K
    7. 212022
    Prev
    Next
    INDEX
    Explanations

    code blocks and lists

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

    It detects structural/formatting elements in the text — headings, emphasized/bolded phrases and other markup-like tokens.

    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_40_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
    ルコ
    0.45
    ukti
    0.43
    পাতের
    0.41
    ϱ
    0.41
    祷
    0.41
    umenical
    0.41
    Columbus
    0.40
     Yards
    0.39
    ඔ
    0.39
    बीआई
    0.38
    POSITIVE LOGITS
     concepts
    0.41
     понятия
    0.40
     ye
    0.39
     thuyết
    0.39
     nervous
    0.38
     download
    0.38
     Download
    0.38
     دانلود
    0.38
     {\
    0.38
     एग्जाम
    0.37
    Activations Density 0.098%

    No Known Activations