© 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. 72389
    Prev
    Next
    INDEX
    Explanations

    Supreme Court

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

    The neuron fires on tokens that are part of article metadata—especially URLs, publication names, and standalone numbers (e.g. “.com,” “LifeNews,” “1,” etc.).

    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
     marché
    -1.02
     serveur
    -0.89
    挙げ
    -0.86
    ý
    -0.85
    resentação
    -0.85
    Ϲ
    -0.85
     technik
    -0.84
     الدوري
    -0.83
     contrô
    -0.82
     armes
    -0.82
    POSITIVE LOGITS
    ształ
    0.84
    フィルター
    0.82
     ensuring
    0.82
     assuring
    0.81
     studied
    0.81
     forester
    0.77
     further
    0.77
     vibrator
    0.77
     apic
    0.77
     insu
    0.75
    Activations Density 0.004%

    No Known Activations