© 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. 3485
    Prev
    Next
    INDEX
    Explanations

    ranked option/recommendation

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

    This neuron detects standalone words in all caps that function as labels or section headings.

    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
     Applicants
    0.61
     SELECTED
    0.59
    袜子
    0.57
    SLE
    0.57
    Applicants
    0.55
    찮
    0.55
    ses
    0.54
     সীমাবদ্ধ
    0.54
     Equations
    0.54
     Commands
    0.53
    POSITIVE LOGITS
    ,//
    0.79
     นาง
    0.69
     녹
    0.64
     hinzuge
    0.64
     erhö
    0.64
     如
    0.63
     มี
    0.63
    rypsin
    0.63
    పీ
    0.62
     ชอบ
    0.62
    Activations Density 0.001%

    No Known Activations