© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 15637
    Prev
    Next
    INDEX
    Explanations

    carrying and lifting objects or people

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

    The neuron fires on verbs describing physically lifting, carrying, or dragging someone or 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_22/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
     εγ
    -1.02
     recuperação
    -1.00
     emisión
    -0.98
    เพิ่ม
    -0.97
     here
    -0.96
    感染
    -0.96
     preocupação
    -0.96
    踝
    -0.94
    ianza
    -0.93
     ligação
    -0.91
    POSITIVE LOGITS
     by
    1.04
    vedad
    0.93
     suspender
    0.90
     suspended
    0.90
    خاذ
    0.87
    בוק
    0.87
     negativos
    0.86
    suspended
    0.85
     into
    0.85
     SUSP
    0.84
    Activations Density 0.069%

    No Known Activations