© 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. 39438
    Prev
    Next
    INDEX
    Explanations

    doctrine

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

    The neuron fires whenever it sees the word “doctrine” (in any context or capitalization).

    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
    螣
    -2.84
    ୌ
    -2.67
     ส์
    -2.61
    饪
    -2.61
    琹
    -2.56
    ꜆
    -2.47
    dzić
    -2.39
    苤
    -2.38
    操作系统
    -2.38
     â
    -2.38
    POSITIVE LOGITS
    </td>
    3.42
    .
    3.20
    <td>
    2.58
     But
    2.48
    </h6>
    2.48
    ↵↵
    2.48
    );
    2.36
    ”，
    2.33
    ”)
    2.27
     AFTER
    2.27
    Activations Density 0.001%

    No Known Activations