© 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. 128849
    Prev
    Next
    INDEX
    Explanations

    Sprite contexts

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

    The neuron is detecting occurrences of the term “Sprite.”

    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
    🧌
    -2.89
    蜘
    -2.58
    鑁
    -2.56
    🫅
    -2.56
    鹩
    -2.55
    饧
    -2.53
    ꦁ
    -2.42
    臯
    -2.41
    岀
    -2.39
    henswürdigkeiten
    -2.38
    POSITIVE LOGITS
    3
    2.84
    6
    2.78
    嗬
    2.61
    8
    2.56
    Through
    2.53
    Because
    2.50
    Having
    2.45
    Ultimately
    2.41
    ・・・・・
    2.41
    ごめんなさい
    2.39
    Activations Density 0.001%

    No Known Activations