© 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
    2. Gemma-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 7983
    Prev
    Next
    INDEX
    Explanations

    MP or mp followed by specific characters

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

    This neuron detects tokens for media file format/metadata codes—particularly “MP” followed by numbers (e.g. MP3, MP4, or size/ID 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_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
    ানো
    0.58
    ingly
    0.53
    を取
    0.51
    dun
    0.51
     recollect
    0.50
     rc
    0.50
    ogna
    0.49
    <>();
    0.49
     नतीजा
    0.49
    endaten
    0.49
    POSITIVE LOGITS
    MP
    0.79
     MP
    0.79
     এমপি
    0.70
     MPP
    0.66
     mp
    0.64
    mp
    0.62
    疑問
    0.61
     MPA
    0.59
     MAKING
    0.59
     ಯಾ
    0.57
    Activations Density 0.032%

    No Known Activations