© 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. 15821
    Prev
    Next
    INDEX
    Explanations

    commands and types

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

    This neuron strongly activates on the last content word at the end of a clause or sentence.

    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
    ט
    0.79
    el
    0.74
     많이
    0.74
    }$
    0.73
    ܢܐ
    0.71
    [
    0.71
    哪些
    0.70
    st
    0.68
    ᆺ
    0.68
     ومل
    0.67
    POSITIVE LOGITS
     Rage
    0.84
     StringBuilder
    0.76
     Aviso
    0.75
     Genres
    0.75
     Pessoa
    0.75
     тип
    0.73
     AppDelegate
    0.73
     Zend
    0.73
    􀂾
    0.73
     Pacífico
    0.72
    Activations Density 0.000%

    No Known Activations