© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 90423
    Prev
    Next
    INDEX
    Explanations

    licensed under Apache

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

    The neuron fires on license‐header lines in source files—especially on “Licensed under …” and related copyright/license declarations.

    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
    cuatro
    -1.49
     for
    -1.49
    عالی
    -1.43
     felicitación
    -1.42
     decisión
    -1.40
     nabízí
    -1.38
     circunstancia
    -1.34
    ⃢
    -1.33
    ໊
    -1.33
     ПРЕ
    -1.31
    POSITIVE LOGITS
     There
    1.38
    無論
    1.35
    就连
    1.35
     Whether
    1.34
     разнообраз
    1.34
     Traditionally
    1.33
     Who
    1.29
    there
    1.28
    Even
    1.27
    From
    1.23
    Activations Density 0.114%

    No Known Activations