© 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. 58056
    Prev
    Next
    INDEX
    Explanations

    de novo

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

    The neuron is tuned to detect occurrences of the substring “novo” (in any case) within tokens.

    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
    ⑊
    -3.06
    ⟞
    -2.98
    
    -2.92
    
    -2.88
     momentous
    -2.75
    罴
    -2.75
     unending
    -2.73
    archiwizowane
    -2.73
    ⏑
    -2.70
     dando
    -2.66
    POSITIVE LOGITS
    It
    3.64
     If
    3.33
    When
    3.25
     When
    3.19
    If
    3.19
    es
    3.00
    櫚
    2.80
     Surprisingly
    2.78
     vehemently
    2.75
    I
    2.73
    Activations Density 0.003%

    No Known Activations