© 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. 22-GEMMASCOPE-RES-131K
    7. 72719
    Prev
    Next
    INDEX
    Explanations

    both X and Y

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

    This neuron detects the word “both,” especially when used in “both … and …” constructions.

    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
    mitir
    -0.98
     this
    -0.93
    ceptre
    -0.91
    的一切
    -0.88
     direct
    -0.87
     such
    -0.85
     further
    -0.85
    martre
    -0.83
     CONTEST
    -0.82
     HIGHLIGHTS
    -0.82
    POSITIVE LOGITS
     nevoie
    1.18
     vaš
    1.14
     telefonu
    1.08
    ACIÓN
    1.07
    гії
    1.04
     klubu
    1.03
    REE
    0.98
    centralwidget
    0.97
    Redis
    0.97
     inš
    0.96
    Activations Density 0.029%

    No Known Activations