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

    Neuronpedia

    Jacobian LensNEW
    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. 7114
    Prev
    Next
    INDEX
    Explanations

    references to AI assistants and large language models, especially self-referential descriptions of the model, tools, and benchmarks (often with dates or platform names)

    oai_token-act-pair · gpt-5Triggered by @vetterc0

    The neuron primarily detects numeric tokens (digits, numerals and year-like numbers) in the text.

    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
    мето
    0.52
    сле
    0.48
     needlessly
    0.47
    counted
    0.46
     традиции
    0.45
    народ
    0.45
    ENSOR
    0.45
    कांची
    0.45
    из
    0.44
    ದ್ದರಿಂದ
    0.43
    POSITIVE LOGITS
     AI
    0.96
     ChatGPT
    0.94
     OpenAI
    0.92
     chatbot
    0.91
     GPT
    0.84
     conversational
    0.80
     chatbots
    0.76
     openai
    0.76
    openai
    0.73
    chatbot
    0.71
    Activations Density 1.397%

    No Known Activations