© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 4195
    Prev
    Next
    INDEX
    Explanations

    carbon dioxide emissions

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

    The neuron activates on references to carbon‐based greenhouse gas emissions (e.g., “CO₂,” “carbon dioxide,” “greenhouse gas,” and “emissions”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    a
    0.69
    江戸
    0.66
    కూ
    0.65
     Fireworks
    0.63
     pail
    0.63
     a
    0.60
    frac
    0.60
    ين
    0.60
    i
    0.59
    д
    0.58
    POSITIVE LOGITS
     மற்றும்
    0.92
     ਅਤੇ
    0.91
     మరియు
    0.90
     ಮತ್ತು
    0.84
     અને
    0.82
     आणि
    0.80
     እና
    0.78
     এবং
    0.76
     và
    0.73
     και
    0.71
    Activations Density 0.016%

    No Known Activations