© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14601
    Prev
    Next
    INDEX
    Explanations

    generating electricity and usable energy

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

    The neuron fires on technical terms and phrases describing electrical power generation or energy‐conversion devices and processes.

    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
    esanan
    -1.16
    畢業
    -1.15
     decirle
    -1.14
    allows
    -1.14
     ochran
    -1.14
    
    -1.12
    mäßige
    -1.11
     Anges
    -1.09
     ихъ
    -1.09
     Bagaimana
    -1.08
    POSITIVE LOGITS
     energy
    1.54
     for
    1.34
     suéter
    1.22
     electricity
    1.18
     sources
    1.13
     from
    1.12
    ゆり
    1.11
    CaseSensitive
    1.10
     metus
    1.09
     output
    1.09
    Activations Density 0.134%

    No Known Activations