© 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. 10-GEMMASCOPE-RES-131K
    7. 112966
    Prev
    Next
    INDEX
    Explanations

    seal, gasket, or gutted

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

    This neuron detects mentions of mechanical sealing components (gaskets, seals, rings, etc.).

    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
    h
    -3.23
    )
    -2.84
    _
    -2.81
    .
    -2.58
    {
    -2.42
    it
    -2.39
    屣
    -2.39
    旆
    -2.28
     "
    -2.20
     ,"
    -2.17
    POSITIVE LOGITS
     encantador
    2.17
    }`;
    2.06
    dade
    2.06
    詎
    1.98
     crux
    1.98
     navn
    1.95
     próxim
    1.92
    <bos>
    1.89
    驀
    1.88
    olition
    1.87
    Activations Density 0.004%

    No Known Activations