© 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. 91348
    Prev
    Next
    INDEX
    Explanations

    logarithm or ln functions

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

    The neuron flags chunks of LaTeX‐style mathematical notation—operators, symbols, and formula commands.

    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
     aconte
    -0.71
     isOpen
    -0.70
    ungguh
    -0.70
    ু
    -0.66
     Wille
    -0.66
    ghijkl
    -0.66
     Haywood
    -0.65
     Zem
    -0.64
     Mary
    -0.64
    ့
    -0.63
    POSITIVE LOGITS
     ln
    4.28
     log
    4.28
    log
    4.06
     logarithm
    4.03
    ln
    3.98
     logarithmic
    3.63
     logarithms
    3.39
     Log
    3.36
     logs
    3.25
    Log
    3.20
    Activations Density 0.214%

    No Known Activations