© 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. 1307
    Prev
    Next
    INDEX
    Explanations

    connector housing interlock mating

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

    The neuron fires on occurrences of technical connector terms—especially “plug,” “connector,” and related coupling or connection words—in electrical/mechanical 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_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
     вет
    -0.73
    каде
    -0.71
     folding
    -0.70
    onzo
    -0.70
    ogado
    -0.69
    Kura
    -0.68
     Schi
    -0.68
     高橋
    -0.68
     eukaryotic
    -0.68
     сво
    -0.67
    POSITIVE LOGITS
    shell
    1.05
     mated
    1.02
     mating
    0.91
    Insert
    0.90
    insert
    0.88
     MATE
    0.85
    Shell
    0.84
    mating
    0.84
    gender
    0.83
     shells
    0.82
    Activations Density 0.048%

    No Known Activations