© 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. 34-GEMMASCOPE-RES-131K
    7. 48024
    Prev
    Next
    INDEX
    Explanations

    didn't or did not

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

    The neuron strongly activates on common personal pronouns (I, you, he, it, we) in running text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    lusst
    -0.89
    ￿
    -0.88
    лями
    -0.85
    ⁃
    -0.84
    begin
    -0.83
    ⁵
    -0.81
    indata
    -0.79
     '-';
    -0.78
    thè
    -0.78
    jsk
    -0.77
    POSITIVE LOGITS
     didn
    6.75
    Didn
    4.56
     Didn
    4.31
    didn
    4.19
     didnt
    3.95
     did
    3.83
     wasn
    2.92
    did
    2.80
    ไม่ได้
    2.78
     Did
    2.69
    Activations Density 0.272%

    No Known Activations