© 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. 34-GEMMASCOPE-RES-131K
    7. 34537
    Prev
    Next
    INDEX
    Explanations

    offshore energy generation

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

    The neuron is highly sensitive to metadata tokens—especially numbers (like years or version identifiers) and all-caps identifiers/acronyms (e.g. license dates, version numbers, “OpenFOAM,” “VGL,” etc.).

    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
    촨
    -0.85
    heat
    -0.76
    Heat
    -0.73
    thermal
    -0.73
     Heiz
    -0.72
    logía
    -0.72
    Hg
    -0.70
    dust
    -0.70
    Thermal
    -0.69
    ָא
    -0.69
    POSITIVE LOGITS
     surge
    0.93
     encounter
    0.88
     hydrodynamic
    0.84
     offshore
    0.84
     Offshore
    0.82
     slamming
    0.79
     heave
    0.78
    Surge
    0.75
     Advisory
    0.75
     onshore
    0.75
    Activations Density 0.013%

    No Known Activations