© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 118760
    Prev
    Next
    INDEX
    Explanations

    mp, mp4, mp3

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

    This neuron activates on tokens beginning with “mp” (as in “mp4,” “mp_chart,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     That
    -2.97
    ل
    -2.88
     They
    -2.58
    轳
    -2.39
     ponieważ
    -2.31
     gdyż
    -2.28
     zumal
    -2.25
     womit
    -2.19
     поэтому
    -2.13
     Ausblick
    -2.06
    POSITIVE LOGITS
    mp
    3.25
    檍
    2.80
    es
    2.69
     laborious
    2.66
     arduous
    2.64
    퐿
    2.64
    饪
    2.53
    釓
    2.50
    ндарт
    2.39
     новой
    2.33
    Activations Density 0.005%

    No Known Activations