© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 59983
    Prev
    Next
    INDEX
    Explanations

    U initialisms and abbreviations

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

    This neuron detects standalone “U” tokens (often as part of biochemical or molecular names and codes, e.g. U-PA, U-FT, U-3840).

    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
    espèce
    -0.85
    balenciaga
    -0.83
    impresa
    -0.82
    zapatillas
    -0.80
     kolorze
    -0.79
    worry
    -0.79
    adillas
    -0.79
     hijau
    -0.79
     veränder
    -0.79
     зробити
    -0.78
    POSITIVE LOGITS
    兔
    0.95
    opia
    0.93
     dönüş
    0.89
    𝐋
    0.86
    versal
    0.86
    TemporalType
    0.86
     Philosophical
    0.85
    робнее
    0.84
    ՞
    0.84
    中共
    0.84
    Activations Density 0.374%

    No Known Activations