© 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. 34-GEMMASCOPE-RES-131K
    7. 50243
    Prev
    Next
    INDEX
    Explanations

    news headlines and disclaimers

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

    The neuron detects the occurrence of the word “Sports” (e.g. in section headers or labels).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     Memiliki
    -0.97
    ltä
    -0.96
     μόνο
    -0.91
    ようですが
    -0.90
    無く
    -0.85
     Menggunakan
    -0.84
    Morfologia
    -0.84
    рения
    -0.84
    Ű
    -0.82
    retario
    -0.80
    POSITIVE LOGITS
    **)
    0.96
     可愛い
    0.93
    oused
    0.90
     therefore
    0.88
    he
    0.85
    や
    0.85
     CGRectMake
    0.85
     ご飯
    0.84
    はかなり
    0.84
    }\}
    0.84
    Activations Density 0.000%

    No Known Activations