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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92957
    Prev
    Next
    INDEX
    Explanations

    liquefied petroleum gas

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

    The neuron strongly responds to technical mentions of liquefied gases (e.g. “liquefied natural gas,” LPG, related chemical names).

    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
    ริง
    -0.82
     movie
    -0.79
     froid
    -0.75
     berken
    -0.74
    movie
    -0.73
    ofon
    -0.73
     romantic
    -0.72
     cuối
    -0.72
    ICATION
    -0.72
    بيب
    -0.71
    POSITIVE LOGITS
     LPG
    2.55
     liquef
    2.30
     Liqu
    2.28
    LPG
    1.93
     liqu
    1.80
    Liqu
    1.55
     lpg
    1.49
     propane
    1.32
     LP
    1.32
    liqu
    1.27
    Activations Density 0.049%

    No Known Activations