© 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. 2374
    Prev
    Next
    INDEX
    Explanations

    *

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

    The neuron activates on HTML markup elements (e.g. `<br>` and `<a>` tags).

    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
    ljanje
    0.92
    рија
    0.88
    ا
    0.88
    وٹی
    0.84
    ak
    0.82
     活动
    0.81
    crypt
    0.80
    ו
    0.79
    льним
    0.79
    ق
    0.78
    POSITIVE LOGITS
    ('$
    0.83
    IN
    0.82
    /><
    0.79
    >^
    0.79
     был
    0.77
    யின்
    0.77
     têm
    0.75
    (">
    0.75
     puta
    0.75
    нодоро
    0.75
    Activations Density 0.002%

    No Known Activations