© 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. 78945
    Prev
    Next
    INDEX
    Explanations

    mechanical components and designs

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

    The neuron specializes in spotting numeric specifications or measurements (e.g. dimension values) in technical passages.

    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
    eapples
    -1.07
    alers
    -1.03
    zelt
    -1.02
     ajudá
    -1.01
    architecte
    -0.99
    ſtre
    -0.97
    atasaray
    -0.97
    іан
    -0.96
     JAXB
    -0.96
     אנשים
    -0.96
    POSITIVE LOGITS
     assembly
    1.45
     designs
    1.34
     assemblies
    1.31
     torque
    1.30
     design
    1.29
     bearings
    1.27
     redesign
    1.21
    design
    1.20
    assembly
    1.15
     failure
    1.13
    Activations Density 0.332%

    No Known Activations