© 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. 13863
    Prev
    Next
    INDEX
    Explanations

    The neuron is a big detector for occurrences of “MUS” (as in the start of “MUSCLE,” i.e. muscle‐related terms).

    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
     Mit
    0.68
     lik
    0.65
     !
    0.63
    mit
    0.62
     *
    0.62
    _
    0.61
     Arch
    0.60
     Democracy
    0.60
     iter
    0.59
     ed
    0.59
    POSITIVE LOGITS
    ྜ
    1.00
    скетбол
    0.98
     девя
    0.91
    classAttribute
    0.91
     برنامه
    0.90
     мульти
    0.90
     бясплатна
    0.88
    𝗈
    0.88
    филлер
    0.87
     दवाई
    0.87
    Activations Density 0.000%

    No Known Activations