© 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. 34-GEMMASCOPE-RES-131K
    7. 58296
    Prev
    Next
    INDEX
    Explanations

    adhesion and bonding

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

    technical descriptions of adhesive materials and bonding properties.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     précise
    -0.88
     templado
    -0.84
    滅
    -0.84
     Бра
    -0.79
    ridor
    -0.78
     WebElement
    -0.78
    кло
    -0.77
    teli
    -0.77
    terday
    -0.77
    ссив
    -0.76
    POSITIVE LOGITS
     adhesion
    1.52
     bond
    1.46
     bonding
    1.33
     bonds
    1.31
     adhering
    1.27
     adhere
    1.21
     adheres
    1.20
    hesion
    1.16
    bond
    1.14
     adhered
    1.13
    Activations Density 0.067%

    No Known Activations