© 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. 43530
    Prev
    Next
    INDEX
    Explanations

    university names and press

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

    The neuron detects mentions of universities or university-affiliated institutions (e.g., “Oxford University,” “Cambridge University”).

    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
    蔔
    -1.69
    其他的
    -1.59
    ianum
    -1.48
     Kühlschrank
    -1.41
    droje
    -1.40
     latter
    -1.39
    surate
    -1.38
     scrapped
    -1.38
    REAM
    -1.37
    LETIN
    -1.36
    POSITIVE LOGITS
     Livro
    1.58
    ༀ
    1.48
     ofreciendo
    1.44
    悧
    1.42
     Ejemplo
    1.41
    =$("#
    1.34
     
    1.30
    Ні
    1.30
    '#
    1.30
     Aluno
    1.28
    Activations Density 0.009%

    No Known Activations