© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 61223
    Prev
    Next
    INDEX
    Explanations

    cement concrete modulus formwork

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

    The neuron consistently fires on specialized engineering or materials‐science terminology—especially concrete and cement product names, formulations, and related technical parameters.

    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
    美国的
    -1.50
    もう一度
    -1.38
     pierwszym
    -1.31
    quần
    -1.30
    接下来的
    -1.30
    わたしは
    -1.30
     antigos
    -1.30
     their
    -1.28
    bộ
    -1.27
     trucos
    -1.27
    POSITIVE LOGITS
     Nö
    1.27
    肇
    1.25
     með
    1.24
    隋
    1.16
    enosti
    1.16
     gonna
    1.16
    URLEncoder
    1.15
    ViewGroup
    1.13
    noStroke
    1.12
    𝑽
    1.12
    Activations Density 0.050%

    No Known Activations