© 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. 6989
    Prev
    Next
    INDEX
    Explanations

    language models trained by Google

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

    tokens used in headings or emphasized/important document structure (bold markers, section numbers, dates, and other emphasis/heading tokens).

    oai_token-act-pair · gpt-5-miniTriggered by @yooniel31

    mentions of AI/LLM model identity and ecosystem details—covering capabilities, training/data specs, APIs, affiliations, and release timelines—especially in the context of Google’s offerings.

    oai_token-act-pair · gpt-5Triggered 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
    Coronavirus
    0.70
     कोरोनावायरस
    0.66
     Coronavirus
    0.64
     coronavirus
    0.59
     করোনাভাই
    0.53
     लॉकडाउन
    0.53
    coronavirus
    0.52
    🖒
    0.52
     коронави
    0.50
    Corona
    0.47
    POSITIVE LOGITS
     ChatGPT
    1.26
    🩷
    1.13
     OpenAI
    1.12
    ChatGPT
    1.09
    🥹
    1.09
    🫶
    1.08
    🫡
    1.04
     ২০২৩
    1.02
    🫠
    1.02
     openai
    1.00
    Activations Density 1.451%

    No Known Activations