© 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. 22-GEMMASCOPE-RES-131K
    7. 130652
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on all‐caps or uppercase sequences—e.g. headings and proper names written entirely in capital letters.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    pioneer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    贸易
    -1.09
    ációs
    -1.02
     useDispatch
    -0.99
     сьогодні
    -0.95
    StandardCharsets
    -0.95
    waktu
    -0.94
     आवश्यकता
    -0.94
    使う
    -0.94
    laştır
    -0.93
     使用
    -0.93
    POSITIVE LOGITS
    uterine
    1.02
    といふ
    0.99
     muros
    0.99
     roads
    0.99
     genitori
    0.97
     czter
    0.97
    年来
    0.96
    calend
    0.96
     lámpara
    0.96
     الحكومة
    0.94
    Activations Density 0.005%

    No Known Activations