© 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. 22-GEMMASCOPE-RES-131K
    7. 39004
    Prev
    Next
    INDEX
    Explanations

    mathematical lemmas and propositions

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

    This neuron detects references to labeled mathematical statements—especially occurrences of “Lemma” (and similar theorem‐type headings).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    ญี่ป
    -1.72
    ̈r
    -1.59
    旆
    -1.55
     فقط
    -1.52
    賸
    -1.52
    ISION
    -1.48
    ㎉
    -1.48
    ЦИЯ
    -1.46
    訁
    -1.46
     persino
    -1.45
    POSITIVE LOGITS
    \
    1.97
    .
    1.74
     if
    1.74
     now
    1.69
     that
    1.59
    ܜ
    1.48
    </td>
    1.48
    cestors
    1.38
    B
    1.36
    ↵↵
    1.35
    Activations Density 0.002%

    No Known Activations