© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 69181
    Prev
    Next
    INDEX
    Explanations

    planar semiconductor transistor

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

    The neuron strongly activates on the technical adjective “planar” when describing engineered structures or devices.

    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
    ٙ
    -2.72
     sacerdotes
    -2.50
    ból
    -2.39
    
    -2.31
     allerlei
    -2.28
     promove
    -2.28
    Etimología
    -2.27
     anún
    -2.23
    ⇴
    -2.23
    鉏
    -2.19
    POSITIVE LOGITS
        
    2.52
    л
    2.47
     he
    2.41
    $
    2.39
    re
    2.38
    You
    2.31
    "
    2.23
    but
    2.19
    本章
    2.14
    3
    2.09
    Activations Density 0.008%

    No Known Activations