© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 9670
    Prev
    Next
    INDEX
    Explanations

    concrete material and applications

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

    The neuron activates on mentions of concrete and closely related cementitious materials (e.g. concrete, cement, mortar, SCC).

    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
    ’
    -2.78
    h
    -2.42
    能在
    -2.23
    és
    -2.14
    d
    -2.09
    知道
    -2.08
    ai
    -1.95
    f
    -1.92
    ING
    -1.88
    自己
    -1.87
    POSITIVE LOGITS
    0
    2.38
    ！】
    1.92
    ዡ
    1.87
     意思
    1.84
    ྥ
    1.80
    酲
    1.80
     It
    1.79
    》。
    1.75
    龊
    1.74
    veloper
    1.73
    Activations Density 0.004%

    No Known Activations