© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 128284
    Prev
    Next
    INDEX
    Explanations

    semiconductor material and devices

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

    The neuron fires on technical semiconductor jargon—especially mentions of “semiconductor” and related band‐structure or doping terms.

    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
     same
    -1.45
    到底是
    -1.27
     lleva
    -1.26
     verschillende
    -1.25
     bezoek
    -1.24
     różnych
    -1.23
    cetos
    -1.23
     dzisiaj
    -1.22
     męska
    -1.22
     obecnie
    -1.21
    POSITIVE LOGITS
    (
    1.34
     .
    1.34
    )
    1.27
     twitch
    1.25
     Boletín
    1.24
     as
    1.22
    .
    1.20
     wil
    1.15
    inescence
    1.15
     TWO
    1.12
    Activations Density 0.155%

    No Known Activations