© 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. 31-GEMMASCOPE-2-RES-16K
    7. 9136
    Prev
    Next
    INDEX
    Explanations

    muskel

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

    The neuron is keyed to the letter sequence “ms,” activating strongly on any token containing those two letters in order.

    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_31_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
     வேற
    0.54
    ンスター
    0.54
    ்ச்ச
    0.53
    单纯
    0.50
    ﺘ
    0.50
    োরে
    0.50
     跳
    0.49
    服
    0.49
     কণ্
    0.49
    ঘুম
    0.48
    POSITIVE LOGITS
     Mosk
    0.63
     Mosca
    0.62
    kipun
    0.60
     Mos
    0.59
    Mos
    0.59
     Mosc
    0.55
     Mus
    0.54
     تنگ
    0.54
    Mus
    0.53
     dargestellt
    0.53
    Activations Density 0.153%

    No Known Activations