© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 40278
    Prev
    Next
    INDEX
    Explanations

    gas pressure expansion

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

    The neuron fires on mathematical expressions in scientific formulas—especially thermodynamics‐style variables (e.g. pV, n, RT) and equation tokens.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    ’).
    -1.00
     "
    -1.00
    logError
    -0.98
    賂
    -0.98
    意味
    -0.95
     woj
    -0.95
     ≠
    -0.95
    ↵
    -0.95
    brtc
    -0.93
    cicle
    -0.92
    POSITIVE LOGITS
     asisten
    1.30
     for
    1.17
     free
    1.15
     ši
    1.12
     freedom
    1.12
     gaseous
    1.11
     vapa
    1.11
    꺾
    1.09
    山下
    1.09
    ковского
    1.09
    Activations Density 0.010%

    No Known Activations