© 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. 98921
    Prev
    Next
    INDEX
    Explanations

    mathematical analysis of algebraic structures

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

    The neuron never fires on any of the tokens shown—it’s effectively a “dead” neuron that finds nothing.

    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
     blatantly
    -1.99
     those
    -1.99
    am
    -1.96
     muualla
    -1.89
     utterly
    -1.84
     ONLY
    -1.84
     there
    -1.80
     supremely
    -1.80
     immensely
    -1.80
     stately
    -1.79
    POSITIVE LOGITS
    盉
    2.03
    쫑
    1.98
     crucial
    1.95
     intriguing
    1.91
    niger
    1.91
    1.89
    analyze
    1.88
    ᷆
    1.88
    齜
    1.84
    
    1.84
    Activations Density 0.007%
    No Known Activations