© 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. 10-GEMMASCOPE-RES-131K
    7. 13341
    Prev
    Next
    INDEX
    Explanations

    badge award or identifier

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

    The neuron activates on occurrences of the word “badge” (in any casing or inflected form).

    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
     he
    -2.75
    祤
    -2.67
    
    -2.67
    睺
    -2.64
    脔
    -2.55
    ⁛
    -2.53
    玏
    -2.52
    鸝
    -2.48
    </h3>
    -2.39
    鸶
    -2.36
    POSITIVE LOGITS
    </b>
    3.83
    可以
    3.31
    Depending
    2.66
    然后
    2.64
    尤其是
    2.58
     hins
    2.56
    section
    2.55
    Within
    2.53
    Regarding
    2.52
    往往
    2.50
    Activations Density 0.002%

    No Known Activations