© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 128960
    Prev
    Next
    INDEX
    Explanations

    sealing punctures and tissue

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

    technical terms related to sealing and connecting materials in industrial or mechanical contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron activates on occurrences of the “seal” stem—e.g. seal, sealed, sealing, sealant—flagging terms that refer to sealing or sealant in the patent text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    汩
    -1.95
    ↵↵
    -1.91
     inquisitive
    -1.90
    ৄ
    -1.88
     mesmerizing
    -1.88
     dreadful
    -1.86
     flamboyant
    -1.81
     "'
    -1.73
     resounding
    -1.70
     agonizing
    -1.70
    POSITIVE LOGITS
    })
    1.77
     sealed
    1.72
     seal
    1.70
    𓆜
    1.67
     bobina
    1.67
     kopling
    1.67
    A
    1.64
     Lubric
    1.63
    さんです
    1.63
    gencias
    1.59
    Activations Density 0.035%

    No Known Activations