© 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. 41861
    Prev
    Next
    INDEX
    Explanations

    unicode escape sequences

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

    The neuron responds to Unicode escape sequences, especially the “\u” prefix and its following hexadecimal digits.

    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
     our
    -1.99
    甞
    -1.96
    ⃢
    -1.75
     any
    -1.67
    Ꮵ
    -1.63
     We
    -1.60
     hablado
    -1.58
     kialak
    -1.54
    溷
    -1.54
     spørsmål
    -1.51
    POSITIVE LOGITS
    ’
    1.54
    訁
    1.52
    this
    1.49
    e
    1.45
     wasn
    1.45
     diminutive
    1.45
    }}\
    1.39
     assassins
    1.39
     detra
    1.38
    更何况
    1.38
    Activations Density 0.013%

    No Known Activations