© 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. 69749
    Prev
    Next
    INDEX
    Explanations

    pick up or collect

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

    The neuron activates on occurrences of “pick up” (including “pickup”/“pick-up”) referring to collecting or receiving something.

    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
    ↵
    -2.48
    E
    -2.34
    0
    -2.27
    O
    -2.22
    D
    -2.22
    f
    -2.20
    or
    -2.17
    ва
    -2.14
    <strong>
    -2.08
    T
    -2.06
    POSITIVE LOGITS
    
    1.83
    簠
    1.82
    趼
    1.78
    瑒
    1.77
    亅
    1.75
     zelen
    1.74
    Fourni
    1.72
     rych
    1.70
     abandonado
    1.69
    鹘
    1.68
    Activations Density 0.028%

    No Known Activations