Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 650
    Prev
    Next
    INDEX
    Explanations

    "what is" followed by definitions

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

    The neuron detects technical or domain-specific terms and acronyms/proper nouns in the assistant's responses.

    oai_token-act-pair · gpt-5-miniTriggered by @yooniel31
    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
     puedan
    0.62
     possano
    0.61
     puissent
    0.57
     pouvaient
    0.55
     possa
    0.52
     puisse
    0.51
     त्यात
    0.47
     possam
    0.47
     podamos
    0.47
     pouvait
    0.46
    POSITIVE LOGITS
    是一种
    1.05
    是一個
    0.92
    是一種
    0.90
    是一个
    0.88
     merupakan
    0.84
     adalah
    0.80
    是一款
    0.78
     является
    0.77
     είναι
    0.76
    是一名
    0.74
    Activations Density 0.259%

    No Known Activations