© 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. 22-GEMMASCOPE-RES-131K
    7. 24959
    Prev
    Next
    INDEX
    Explanations

    data collection and analysis

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

    The neuron fires on business‐analytics terminology, especially words related to customer data, accounts, and management.

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    گوشی
    -1.67
    ὴν
    -1.50
     ویتامین
    -1.20
    ׇ
    -1.19
    ῖν
    -1.19
    мани
    -1.15
     minha
    -1.13
    ومن
    -1.09
     wisata
    -1.09
     ganador
    -1.09
    POSITIVE LOGITS
     data
    2.33
     collected
    1.62
     information
    1.38
     such
    1.31
     from
    1.30
     every
    1.25
    data
    1.24
     Data
    1.23
     getData
    1.19
     collect
    1.12
    Activations Density 0.079%

    No Known Activations