© 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. 83692
    Prev
    Next
    INDEX
    Explanations

    stretch and elasticity

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

    The neuron fires on words and word pieces that express stretchiness or elastic/extensible material properties.

    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
    Spurs
    -0.71
     HISTORICAL
    -0.71
     aborto
    -0.71
    robe
    -0.70
     Complexity
    -0.69
    زیین
    -0.68
    Tamaño
    -0.68
     Kissinger
    -0.68
     tilted
    -0.67
     congel
    -0.67
    POSITIVE LOGITS
     stretch
    3.48
    stretch
    3.02
     Stretch
    2.98
    Stretch
    2.75
     stretchy
    2.73
     stretching
    2.66
     stretches
    2.66
    stret
    2.45
     stret
    2.45
     Stret
    2.22
    Activations Density 0.022%

    No Known Activations