© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57255
    Prev
    Next
    INDEX
    Explanations

    museums and institutions

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

    The neuron activates strongly on proper names—i.e. named entities such as places, institutions, exhibitions, and other capitalized titles.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     società
    -0.80
    cephala
    -0.75
    ahas
    -0.70
    sensi
    -0.67
    Imo
    -0.67
    Plen
    -0.66
    kirch
    -0.66
    脐
    -0.66
     plenary
    -0.65
    Clown
    -0.65
    POSITIVE LOGITS
     Crystal
    1.16
    Crystal
    1.08
     Prince
    1.03
     Franco
    1.03
    Prince
    0.97
     Exhibition
    0.94
     Kensington
    0.90
     Albert
    0.88
     crystal
    0.88
    crystal
    0.86
    Activations Density 0.059%

    No Known Activations