© 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. 85928
    Prev
    Next
    INDEX
    Explanations

    Drake, Aubrey, Q

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

    The neuron strongly activates on tokens containing the letter sequence “dra” (as in “Drake,” “Drizzy,” or “DRA”).

    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
    "
    -3.20
    ⽼
    -3.05
     \_
    -2.75
    ed
    -2.72
    的就
    -2.67
    P
    -2.59
    \
    -2.58
     $\
    -2.48
    ى
    -2.48
    on
    -2.44
    POSITIVE LOGITS
    衄
    2.56
    詒
    2.56
     dasarnya
    2.56
     signifikan
    2.56
    錀
    2.55
     pandangan
    2.42
     ujedno
    2.41
    あるので
    2.39
    鶚
    2.38
     една
    2.31
    Activations Density 0.002%

    No Known Activations