© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 57998
    Prev
    Next
    INDEX
    Explanations

    mathematical conjectures and theorems

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

    The neuron fires on formal mathematical terminology—especially words like “equation,” “theorem,” “theory,” and other domain-specific math nouns.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    zepam
    -1.38
     firepower
    -1.24
     scammed
    -1.24
    ὡ
    -1.23
    enerys
    -1.22
     Obamacare
    -1.20
     Hobbes
    -1.20
    ghold
    -1.18
    горе
    -1.17
    igata
    -1.17
    POSITIVE LOGITS
     such
    1.19
     evidenced
    1.17
    </u>
    1.17
     even
    1.16
    ΢
    1.07
    ことがある
    1.04
    ご覧ください
    1.02
     incluso
    1.01
     champignons
    1.01
    ````
    1.00
    Activations Density 0.066%

    No Known Activations