© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 14234
    Prev
    Next
    INDEX
    Explanations

    purpose is to provide

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

    the neuron fires on discussions of political or civic institutions and related governance terms.

    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
     довольно
    0.92
     hauptsächlich
    0.92
     sneaky
    0.90
     fréquence
    0.89
     whopping
    0.88
    ôtels
    0.88
     abnormally
    0.86
    뺨
    0.86
    extrémité
    0.85
    ógrafo
    0.84
    POSITIVE LOGITS
     Democracy
    1.34
     democracy
    1.27
     democratic
    1.25
     demokrasi
    1.22
     unity
    1.20
     solidar
    1.20
     solidarity
    1.17
     Solidarity
    1.16
     solidaridad
    1.16
     Unity
    1.10
    Activations Density 1.321%

    No Known Activations