© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91426
    Prev
    Next
    INDEX
    Explanations

    proactively deter

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

    The neuron fires on capitalized tokens that make up formal entity names—especially military units, honours, and organizational 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
    Jeśli
    -0.94
    説明
    -0.85
    亞洲
    -0.84
    koń
    -0.83
    RELATED
    -0.82
    Плюсы
    -0.82
    Татьяна
    -0.81
    Przeczytaj
    -0.79
    Новые
    -0.79
     aprendiz
    -0.78
    POSITIVE LOGITS
    PSY
    0.90
     ashore
    0.89
     deprecated
    0.88
    нодоро
    0.88
     promulgated
    0.88
    AnimationsModule
    0.85
    sizePolicy
    0.84
     melaksanakan
    0.84
    имость
    0.84
     chk
    0.83
    Activations Density 0.018%

    No Known Activations