© 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. 34-GEMMASCOPE-RES-131K
    7. 79194
    Prev
    Next
    INDEX
    Explanations

    Sch- names

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

    The neuron is tuned to detect the dense numeric and stock‐ticker/date tokens characteristic of corporate press releases—e.g. years, share prices, dividend amounts, NASDAQ symbols, and similar financial‐report numbers.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    entum
    -1.02
     pulito
    -0.84
    gone
    -0.79
     resulting
    -0.79
     preços
    -0.78
    Karriere
    -0.77
     possibili
    -0.75
     nuoc
    -0.75
     lunghi
    -0.75
     इसका
    -0.75
    POSITIVE LOGITS
    Sch
    1.10
     Sch
    0.98
    muje
    0.77
     सबसे
    0.77
     SCH
    0.77
    Collect
    0.76
     بسیاری
    0.75
    人人
    0.75
    uzzi
    0.75
    SCH
    0.74
    Activations Density 0.041%

    No Known Activations