© 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. 71668
    Prev
    Next
    INDEX
    Explanations

    vehicles and containers

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

    This neuron detects expressions of exiting or getting “out of” something—particularly disembarking from vehicles.

    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
     that
    -1.59
     is
    -1.38
     $
    -1.10
     ähnlich
    -1.09
    that
    -1.09
     away
    -1.06
     äußerst
    -1.06
     "
    -1.05
    zanie
    -1.05
     therefore
    -1.03
    POSITIVE LOGITS
    bilde
    1.23
     swój
    1.14
    تين
    1.14
     lignin
    1.12
    れてる
    1.11
    rechter
    1.09
     olduk
    1.08
    禤
    1.08
    🍖
    1.08
     penting
    1.07
    Activations Density 0.017%

    No Known Activations