© 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. 10382
    Prev
    Next
    INDEX
    Explanations

    facing criticism

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

    This neuron responds to capitalized names—like brands, titles, or 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
    ik
    0.97
    ן
    0.86
    ic
    0.82
     provinsi
    0.80
    yecto
    0.78
    estructura
    0.78
     Eti
    0.78
    ositol
    0.77
    inerja
    0.76
    odom
    0.75
    POSITIVE LOGITS
     他
    0.84
     modestly
    0.77
    囚
    0.76
     被
    0.73
     vấn
    0.73
     次
    0.72
     raff
    0.71
    嘭
    0.71
     가진
    0.70
    まず
    0.70
    Activations Density 0.001%

    No Known Activations