© 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
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 223
    Prev
    Next
    INDEX
    Explanations

    achievement, science, culture, exploration

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

    This neuron detects mentions of specific academic or topical fields (like history, law, politics, art, energy, transportation, etc.).

    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
     stb
    0.50
    Several
    0.46
     VERY
    0.44
     $(
    0.41
     κατά
    0.40
    ﺽ
    0.40
     Several
    0.39
     ${
    0.38
     usw
    0.38
     о
    0.38
    POSITIVE LOGITS
    ainment
    0.63
     ciencia
    0.57
     scienze
    0.54
     scienza
    0.53
     науки
    0.52
     لیکن
    0.52
    esthetics
    0.52
    ievement
    0.52
    ivism
    0.51
    iteracy
    0.50
    Activations Density 0.000%

    No Known Activations