© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 69926
    Prev
    Next
    INDEX
    Explanations

    carrying objects or people

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

    This neuron fires most strongly on high-frequency function words and common short tokens (e.g. “is,” “to,” “it,” commas), i.e. English stopwords and punctuation.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    ctis
    -0.82
    estión
    -0.74
    ará
    -0.72
     сюда
    -0.69
    atau
    -0.69
    mentaux
    -0.69
    propane
    -0.66
    elem
    -0.65
    setContent
    -0.65
    移
    -0.65
    POSITIVE LOGITS
     carrying
    6.44
     carry
    6.31
    carrying
    5.69
    Carrying
    5.53
     carries
    5.53
     Carrying
    5.47
    Carry
    5.44
    carry
    5.44
     Carry
    5.34
     CARRY
    5.13
    Activations Density 0.128%

    No Known Activations