© 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. 34-GEMMASCOPE-RES-131K
    7. 99171
    Prev
    Next
    INDEX
    Explanations

    material properties and ease of use

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

    The neuron is detecting positive quality and durability–focused descriptive adjectives (e.g. lightweight, sturdy, resistant, professional) in product descriptions.

    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
    aneity
    -1.16
    geddon
    -1.07
    ectomy
    -1.05
    onomies
    -1.04
    ('-'
    -1.02
    vermectin
    -1.02
    welli
    -0.99
    imeter
    -0.97
    thodoxy
    -0.96
    ograph
    -0.95
    POSITIVE LOGITS
     durable
    2.64
     waterproof
    1.98
     lightweight
    1.73
     easy
    1.59
     resistant
    1.59
     Durable
    1.56
     sturdy
    1.48
     resilient
    1.47
     durability
    1.47
     corrosion
    1.42
    Activations Density 0.061%

    No Known Activations