© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 131013
    Prev
    Next
    INDEX
    Explanations

    The neuron detects mentions of quantified infrastructure changes or improvements—tokens that convey measured actions (like narrowing lanes by a specific number of feet or adding X space) or other numeric, measure-based modifications.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    road infrastructure and traffic controls

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    você
    -1.49
     اپنے
    -1.47
    eapples
    -1.39
    Primeiro
    -1.36
    :"",
    -1.33
    quido
    -1.30
     olabilir
    -1.29
    mmers
    -1.29
    ٱ
    -1.28
    Nederlands
    -1.27
    POSITIVE LOGITS
     on
    1.45
     actionTypes
    1.35
    рен
    1.34
    ๘
    1.30
     design
    1.30
     pintadas
    1.27
     тип
    1.21
     installation
    1.20
     street
    1.20
     configuration
    1.20
    Activations Density 0.026%

    No Known Activations