© 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. 22-GEMMASCOPE-RES-131K
    7. 130459
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on ALL-CAP letter sequences (e.g., acronyms, enum‐style constants, or other fully uppercase identifiers).

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

    code or instruction completion

    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
    。
    -1.13
    u
    -1.10
     The
    -1.09
    s
    -1.05
    /
    -1.03
    Ð
    -1.03
    </h4>
    -1.01
     proporciona
    -1.00
     обрабо
    -1.00
     všetkých
    -0.98
    POSITIVE LOGITS
    赈
    1.27
    📮
    1.25
    復興
    1.24
    鏖
    1.22
    特長
    1.20
    災害
    1.16
    Aya
    1.13
    饗
    1.13
     дату
    1.12
    书法
    1.12
    Activations Density 0.000%

    No Known Activations