© 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. 14170
    Prev
    Next
    INDEX
    Explanations

    dj followed by names or acronyms

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

    The neuron strongly activates on the two-letter token “dj” (in either lower-case or upper-case form).

    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
    .“
    -3.52
     entsprechende
    -2.67
    7
    -2.61
     \
    -2.55
    ，“
    -2.48
    稣
    -2.44
    、“
    -2.39
     "";
    -2.39
    。“
    -2.38
    他
    -2.36
    POSITIVE LOGITS
    se
    2.39
    隳
    2.34
    ♡♡
    2.34
     utilisons
    2.28
    躪
    2.16
    嵎
    2.16
    琿
    2.13
     公园
    2.11
    ፧
    2.09
    邙
    2.09
    Activations Density 0.003%

    No Known Activations