© 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. 22-GEMMASCOPE-RES-131K
    7. 66850
    Prev
    Next
    INDEX
    Explanations

    during construction and protection

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

    The neuron fires on concrete countable nouns for physical objects, materials, debris, or equipment typically found on a construction or industrial work site.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     оружия
    -1.36
    Questão
    -1.30
     ligação
    -1.27
    Objetivos
    -1.27
     муки
    -1.24
     relógio
    -1.23
     gostar
    -1.18
     distância
    -1.18
     you
    -1.16
    だけです
    -1.16
    POSITIVE LOGITS
     during
    2.47
    During
    1.42
    stringBuffer
    1.34
    Durante
    1.30
    岀
    1.28
    monių
    1.27
     दौरान
    1.27
    ėtų
    1.27
     kreatif
    1.27
    任何
    1.25
    Activations Density 0.003%

    No Known Activations