© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 75602
    Prev
    Next
    INDEX
    Explanations

    fluxes and rates

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

    The neuron spots scientific or mathematical jargon—especially physical‐science terms (like flux, diffusion, methane) and math notation (e.g. ∇⋅, vector symbols, numbered equations).

    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
     temperature
    -0.96
     temperatura
    -0.94
     temperatures
    -0.84
    temperature
    -0.83
     Prices
    -0.81
     prices
    -0.77
     HttpStatus
    -0.76
    Boost
    -0.75
     smash
    -0.75
     userDao
    -0.73
    POSITIVE LOGITS
     flux
    1.86
     fluxes
    1.66
    flux
    1.50
     rate
    1.44
     Flux
    1.43
    Flux
    1.40
     RATES
    1.30
     rates
    1.30
    RATE
    1.27
    Rate
    1.22
    Activations Density 0.036%

    No Known Activations