© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101466
    Prev
    Next
    INDEX
    Explanations

    part of the

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

    The neuron activates on the word “part” when used in “part of” constructions.

    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
    .
    -1.99
     Bedürfn
    -1.88
     with
    -1.84
    9
    -1.80
     by
    -1.73
        
    -1.58
    There
    -1.57
    borsa
    -1.49
    ↵↵
    -1.48
           
    -1.48
    POSITIVE LOGITS
     イラストレーション
    1.90
    蠃
    1.85
    
    1.80
    ógico
    1.74
     eikä
    1.67
     ergon
    1.67
     frequentemente
    1.66
    >
    1.65
     facilita
    1.62
    quelize
    1.60
    Activations Density 0.024%

    No Known Activations