© 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. 104652
    Prev
    Next
    INDEX
    Explanations

    knockout mutation or mice

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

    The neuron detects the term "knockout" in scientific and technical contexts, particularly in genetics and biology research papers.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    0
    -3.41
    栳
    -2.94
    ve
    -2.53
    嫱
    -2.47
    t
    -2.41
    ting
    -2.36
    AdvEx
    -2.30
    ”
    -2.30
    </h4>
    -2.27
     been
    -2.27
    POSITIVE LOGITS
    
    2.61
    ！】
    2.58
     și
    2.33
     prioritise
    2.25
    ที่
    2.20
    ان
    2.19
    و
    2.16
     triệu
    2.14
     werfen
    2.14
    ༛
    2.11
    Activations Density 0.007%

    No Known Activations