© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 9688
    Prev
    Next
    INDEX
    Explanations

    why it

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

    The neuron is detecting very common function words (high‐frequency pronouns, articles, auxiliaries, and question words).

    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
    事先
    0.57
    麼
    0.55
     двух
    0.55
    又不
    0.54
    ственную
    0.54
    чный
    0.54
     صورة
    0.53
     inpatient
    0.52
    чної
    0.52
     двох
    0.51
    POSITIVE LOGITS
     it
    1.13
    它
    1.03
    มัน
    0.99
     它
    0.99
     thereof
    0.98
    它的
    0.97
     ĝi
    0.94
     มัน
    0.91
     వాటి
    0.90
    它們
    0.88
    Activations Density 0.777%

    No Known Activations