© 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. 27031
    Prev
    Next
    INDEX
    Explanations

    new construction of facilities

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

    The neuron fires strongly on mentions of major public‐infrastructure projects or facilities (e.g. airports, parks, schools, hospitals, power plants, quarries).

    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
    っている
    -1.30
     semelh
    -1.23
     tarjo
    -1.18
    envoyer
    -1.17
     olduk
    -1.16
     kanilang
    -1.13
     représenter
    -1.12
    q
    -1.11
     Giugno
    -1.11
     beweisen
    -1.11
    POSITIVE LOGITS
     in
    1.95
     will
    1.31
     project
    1.30
     on
    1.29
    ！"
    1.27
     built
    1.25
     planned
    1.24
     at
    1.21
     new
    1.20
     operador
    1.13
    Activations Density 0.060%

    No Known Activations