© 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. 34-GEMMASCOPE-RES-131K
    4. 60014
    Prev
    Next
    INDEX
    Explanations

    special characters and foreign words

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

    The neuron strongly activates on the Latin letter “o” with a macron (ō), i.e. vowels bearing a macron diacritic.

    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
     Incenti
    -0.82
     Pali
    -0.77
    ┻
    -0.74
     powerpoint
    -0.74
     formie
    -0.72
    ㅋ
    -0.71
     меч
    -0.71
     Sympathi
    -0.68
    Jx
    -0.68
    normalization
    -0.66
    POSITIVE LOGITS
     dů
    0.89
    posed
    0.84
    めている
    0.74
    깊
    0.73
     Versicher
    0.71
    wede
    0.71
    puestas
    0.70
    MIS
    0.70
    ֹ
    0.70
    topic
    0.70
    Activations Density 0.030%

    No Known Activations