© 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. 2438
    Prev
    Next
    INDEX
    Explanations

    sections or lists

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

    This neuron strongly activates on named entities and other proper nouns.

    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
     プロ
    0.76
    ↻
    0.75
    Climate
    0.75
     環境
    0.70
    s
    0.69
    คลิ
    0.68
    0.68
     errore
    0.68
    ों
    0.68
    🧬
    0.68
    POSITIVE LOGITS
    itable
    0.89
    operated
    0.85
     vemos
    0.82
    ковая
    0.81
     earners
    0.80
    ल्तान
    0.79
     liye
    0.78
     parece
    0.77
     quitter
    0.77
    ফান
    0.77
    Activations Density 0.001%

    No Known Activations