© 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. 69489
    Prev
    Next
    INDEX
    Explanations

    mind, bodied, palsy

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

    The neuron activates on the idiomatic phrase “bear in mind” (including its gerund form “bearing in mind”).

    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
    </h4>
    -2.17
    </h1>
    -2.03
    i
    -1.79
    </h5>
    -1.71
     или
    -1.66
    </b>
    -1.64
    0
    -1.63
    }>
    -1.58
     "..\..\..\
    -1.55
    )
    -1.55
    POSITIVE LOGITS
    烀
    1.84
     honom
    1.72
    ௜
    1.71
    櫚
    1.70
    ▤
    1.50
     memerlukan
    1.46
     Ense
    1.44
    ettbewerb
    1.44
    
    1.44
    !!,
    1.42
    Activations Density 0.002%

    No Known Activations