© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 128690
    Prev
    Next
    INDEX
    Explanations

    í with accents

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

    The neuron activates on Latin letters bearing diacritical marks (e.g. accented characters like í, ñ).

    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
    2
    -3.64
    7
    -2.56
    Kelebihan
    -2.52
     zweiten
    -2.42
    趼
    -2.38
     Approximately
    -2.36
     großen
    -2.33
     einer
    -2.33
    8
    -2.33
    $,
    -2.27
    POSITIVE LOGITS
    ’
    3.11
    鼱
    2.89
    s
    2.84
    鹉
    2.78
    嗵
    2.77
    璨
    2.73
    圌
    2.72
     corpi
    2.72
    埽
    2.64
    蹰
    2.58
    Activations Density 0.004%

    No Known Activations