© 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. 59428
    Prev
    Next
    INDEX
    Explanations

    uranium dioxide or mining

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

    references to uranium and other radioactive elements or nuclear materials.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron activates on mentions of uranium (and related actinide) compounds, especially uranium dioxide and similar chemical species.

    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
    ’
    -2.56
    koszulka
    -2.14
    ۔
    -2.13
     стоковая
    -1.97
     étroite
    -1.94
    耜
    -1.92
     costumbres
    -1.91
    。
    -1.88
    呶
    -1.88
     populaires
    -1.87
    POSITIVE LOGITS
    .
    2.58
     of
    2.44
     to
    2.08
    ,
    1.95
    ある
    1.92
    N
    1.91
    あるので
    1.88
    D
    1.88
    K
    1.86
     It
    1.80
    Activations Density 0.010%

    No Known Activations