© 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. 33690
    Prev
    Next
    INDEX
    Explanations

    RunwayML, Golden Gai, grew on me

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

    The neuron detects mentions of proper nouns—especially well-known product or brand names (e.g., AI tools) and other capitalized names.

    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
    䏌
    0.43
     vegetarian
    0.42
    oltre
    0.38
    isure
    0.37
    劣
    0.37
    風
    0.37
     hens
    0.37
    ใด
    0.37
     ত্র
    0.36
     affluent
    0.36
    POSITIVE LOGITS
    Rand
    0.47
     Rand
    0.46
    Brad
    0.46
     Brad
    0.43
     nash
    0.37
     prov
    0.37
     rand
    0.37
     Gai
    0.37
     эксперимента
    0.37
    炀
    0.37
    Activations Density 0.003%

    No Known Activations