© 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. 5306
    Prev
    Next
    INDEX
    Explanations

    numbers followed by `op` or `admon`

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

    The neuron is a detector for HTML markup tokens (e.g. “<em>”) and other inline formatting/metadata 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
     жүктөө
    0.82
    ATTR
    0.81
    ENDER
    0.80
    ENSIVE
    0.78
    𝙈
    0.78
     rulemaking
    0.77
    CONN
    0.76
    𝘽
    0.75
    ENDMENT
    0.74
     inoculum
    0.74
    POSITIVE LOGITS
    mem
    0.81
    .
    0.78
    am
    0.74
    ik
    0.74
    templ
    0.72
    -
    0.72
     supérieur
    0.71
     Which
    0.70
    濰
    0.70
    :
    0.69
    Activations Density 0.001%

    No Known Activations