© 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. 10-GEMMASCOPE-RES-131K
    7. 43104
    Prev
    Next
    INDEX
    Explanations

    conductors, wires, and strands

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

    The neuron responds to technical component nouns—especially parts of cables or electrical assemblies (e.g. core, strand, sheath, conductor).

    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
     both
    -1.34
    шень
    -1.24
    ing
    -1.23
    産の
    -1.23
     beide
    -1.19
     لإ
    -1.18
    所の
    -1.18
    "}>
    -1.16
     itinéraire
    -1.13
     Unión
    -1.12
    POSITIVE LOGITS
     résult
    1.46
    いよいよ
    1.40
     zugelassen
    1.30
     festgelegt
    1.29
     chronicles
    1.28
    Clar
    1.26
     Erinnerungen
    1.24
    acteur
    1.23
    나는
    1.23
    夘
    1.22
    Activations Density 0.085%

    No Known Activations