© 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. 10-GEMMASCOPE-RES-131K
    7. 21031
    Prev
    Next
    INDEX
    Explanations

    building parts: window, doors, roof, floors, wall, door

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

    The neuron fires on words that denote physical openings or access points in an object—like openings, windows, doors, ports, pockets, or zippers.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     HISTORIA
    -1.34
     olímp
    -1.23
     näh
    -1.13
     YEAH
    -1.12
     cyclisme
    -1.10
    __':
    -1.08
    evich
    -1.08
     Ciencias
    -1.08
    ützen
    -1.07
     infinita
    -1.07
    POSITIVE LOGITS
     They
    1.50
     you
    1.40
     =
    1.32
    渡し
    1.23
    出して
    1.21
     spesso
    1.13
     for
    1.12
     <
    1.09
     your
    1.09
     scri
    1.09
    Activations Density 0.090%

    No Known Activations