© 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. 10-GEMMASCOPE-RES-131K
    7. 65806
    Prev
    Next
    INDEX
    Explanations

    gemstones and associated terms

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

    The neuron activates on mentions of gemstone names (e.g. Emerald, Opal, Topaz).

    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
    ꦢ
    -3.05
    翃
    -3.05
    饜
    -3.02
    癶
    -3.00
    癰
    -2.81
    ⢪
    -2.78
    摀
    -2.72
    Ᏻ
    -2.70
     baterie
    -2.69
    憷
    -2.58
    POSITIVE LOGITS
    ;
    3.22
    ’
    3.11
    我们可以
    2.75
    –
    2.45
    One
    2.44
    From
    2.38
    wg
    2.34
     Surprisingly
    2.33
    Even
    2.30
    話の
    2.28
    Activations Density 0.003%

    No Known Activations