© 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. 10-GEMMASCOPE-RES-131K
    7. 69837
    Prev
    Next
    INDEX
    Explanations

    construction status and costs

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

    The neuron strongly activates on mentions of construction work (especially the token “construction” and its close variants).

    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
    ῞
    -1.85
    formatics
    -1.66
    cursions
    -1.64
    をします
    -1.60
    スポンサーリンク
    -1.49
     berdua
    -1.48
    </h2>
    -1.47
     simplifies
    -1.45
     siguientes
    -1.45
    ▢
    -1.45
    POSITIVE LOGITS
    jadikan
    1.58
    </code>
    1.57
     This
    1.48
     These
    1.45
     to
    1.44
    ặp
    1.41
     недорого
    1.41
    嵛
    1.41
     is
    1.40
     forbindelse
    1.39
    Activations Density 0.026%

    No Known Activations