© 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. 69082
    Prev
    Next
    INDEX
    Explanations

    institutional buildings and sites

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

    The neuron identifies the names of institutions, organizations, or venue locations (e.g., schools, museums, churches, centers).

    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
    k
    -1.17
    f
    -1.13
    c
    -1.07
    d
    -1.06
    -1.05
    p
    -1.05
    ,
    -1.05
    F
    -1.02
    u
    -1.02
    -
    -1.01
    POSITIVE LOGITS
    []}
    1.23
     at
    1.22
     on
    1.17
    ⃙
    1.16
    🎹
    1.16
    ſtra
    1.11
    voer
    1.11
    nál
    1.09
     ingredientes
    1.09
     ț
    1.08
    Activations Density 0.040%

    No Known Activations