© 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. 1766
    Prev
    Next
    INDEX
    Explanations

    locations of physical parts

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

    The neuron selectively flags mentions of concrete technical components or interfaces (e.g., ports, valves, orifices, terminals).

    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
     deinen
    -1.10
     organizza
    -0.98
     deose
    -0.95
    졍
    -0.94
     heut
    -0.90
     sarebbe
    -0.90
     wenigstens
    -0.89
     hinsichtlich
    -0.89
    有很多
    -0.89
     additionally
    -0.89
    POSITIVE LOGITS
     on
    1.73
     located
    1.69
     of
    1.40
    located
    1.36
     situated
    1.34
    Located
    1.30
     расположен
    1.27
     in
    1.20
     Located
    1.13
     belonging
    1.12
    Activations Density 0.116%

    No Known Activations