© 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. 53-GEMMASCOPE-2-RES-262K
    7. 4202
    Prev
    Next
    INDEX
    Explanations

    defining or explaining specific terms

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

    the neuron detects prominent topical content words—key domain-specific nouns and concepts in expository or informational 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_53_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
     এটাই
    0.51
     وبالتالي
    0.49
    इसलिए
    0.47
     সেটাই
    0.47
     অতএব
    0.45
    だから
    0.44
    함으로써
    0.43
     وهذا
    0.43
     ইহাই
    0.43
     BECAUSE
    0.42
    POSITIVE LOGITS
     whereby
    0.66
     waarbij
    0.61
     wherein
    0.56
     wobei
    0.54
     إذ
    0.51
     inasmuch
    0.45
     αφού
    0.44
     โดย
    0.43
     असून
    0.43
     insofar
    0.43
    Activations Density 0.253%

    No Known Activations