© 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. 2071
    Prev
    Next
    INDEX
    Explanations

    societal and economic progress

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

    The neuron activates on positive evaluative or promotional terms—especially superlatives and enhancement words (e.g. optimal, enhanced, advanced, incredible, stronger).

    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
    0
    1.04
    5
    0.96
    4
    0.96
    3
    0.94
    1
    0.94
    2
    0.93
    8
    0.88
    7
    0.88
    6
    0.87
    0.86
    POSITIVE LOGITS
     économique
    0.99
     morbidity
    0.96
     biodiversity
    0.92
     sociali
    0.89
     economico
    0.88
     infrastructural
    0.85
     culturali
    0.85
     socioeconomic
    0.85
     motility
    0.84
     psychosocial
    0.84
    Activations Density 0.669%

    No Known Activations