© 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. 255
    Prev
    Next
    INDEX
    Explanations

    system commands and file paths

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

    This neuron strongly activates on tokens that begin sentences (i.e. the first token after a sentence boundary).

    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
    Stuart
    0.80
    k
    0.80
    til
    0.79
    K
    0.73
    是我们
    0.72
    ्स
    0.71
     Roberta
    0.71
    㳓
    0.70
     Taylor
    0.70
     Stuart
    0.69
    POSITIVE LOGITS
    ﹌
    0.80
     tên
    0.75
    ignation
    0.74
    𓃵
    0.72
     BBBB
    0.69
    elenggarakan
    0.69
    saveTool
    0.69
    ベーション
    0.68
     sinned
    0.68
     tuy
    0.68
    Activations Density 0.000%

    No Known Activations