© 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. 22-GEMMASCOPE-RES-131K
    4. 39985
    Prev
    Next
    INDEX
    Explanations

    construction start

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

    The neuron activates on words and phrases that denote the initiation or planned start of a project—e.g. “start,” “began,” “construction,” “expected to.”

    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
     their
    -1.18
    werden
    -1.18
    >--}}
    -1.15
    ſo
    -1.06
    诋
    -1.02
     Зачем
    -1.02
    mereka
    -1.02
     perigo
    -1.01
     variety
    -1.00
     Situationen
    -1.00
    POSITIVE LOGITS
     construction
    1.38
     begun
    1.27
     comenzará
    1.25
     commenced
    1.21
     started
    1.20
    startDate
    1.20
     already
    1.17
     about
    1.17
     izquier
    1.17
     undertaken
    1.16
    Activations Density 0.033%

    No Known Activations