© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 70653
    Prev
    Next
    INDEX
    Explanations

    ROI, FTIR, cerebellum, interaction, SS

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

    The neuron is looking for the acronym "ROI" and related terms like "region of interest".

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron is triggered by occurrences of the substring “roi” (most notably the acronym ROI).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    );
    -2.52
    )
    -2.23
     啦
    -2.20
     использованием
    -2.19
     pointless
    -2.19
     吗
    -2.16
     почти
    -2.14
    蔼
    -2.09
     drogi
    -2.09
    ↵
    -2.05
    POSITIVE LOGITS
    
    2.88
    ’
    2.36
    —
    2.34
    (
    2.30
    黑衣
    2.28
     semblait
    2.28
     anún
    2.19
    ❓
    2.16
    </strong>
    2.14
     améli
    2.14
    Activations Density 0.002%

    No Known Activations