© 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. 10-GEMMASCOPE-RES-131K
    7. 43659
    Prev
    Next
    INDEX
    Explanations

    related followed by subject

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

    The neuron detects occurrences of the word “related,” as in headings or references to related work or literature.

    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
    </h1>
    -1.86
     by
    -1.76
     dokład
    -1.70
    </u>
    -1.63
     deformed
    -1.63
    льзя
    -1.58
    istica
    -1.56
     The
    -1.54
    出て
    -1.54
     "
    -1.53
    POSITIVE LOGITS
     emporio
    2.16
     garten
    2.06
     rosario
    1.98
     中式
    1.95
    縂
    1.94
    茈
    1.92
     ſch
    1.92
     busto
    1.90
     alemania
    1.79
     hjemmes
    1.77
    Activations Density 0.048%

    No Known Activations