© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 41074
    Prev
    Next
    INDEX
    Explanations

    chemical energy, fuels, and electricity

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

    words and concepts related to chemical compounds, fuels, and energy production processes.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires on mentions of chemical substances or formulas (e.g., H₂, NH₃, methanol, ammonia, fuel, chemical).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    了一会儿
    -1.34
     They
    -1.33
    received
    -1.29
     nevera
    -1.26
     детской
    -1.23
    りましたが
    -1.22
    semi
    -1.21
    ⊇
    -1.21
    they
    -1.20
    没问题
    -1.20
    POSITIVE LOGITS
    ឧ
    1.27
     salita
    1.19
     what
    1.18
     until
    1.13
    Tors
    1.13
     before
    1.13
     without
    1.12
     skep
    1.12
    andidat
    1.11
    特集
    1.11
    Activations Density 0.215%

    No Known Activations