© 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. 10078
    Prev
    Next
    INDEX
    Explanations

    mi or MI followed by certain words

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

    The neuron strongly fires on occurrences of the two-letter string “Mi” at the start of tokens.

    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
    ঠিত
    0.61
     دم
    0.55
     बनाए
    0.54
    MANIFEST
    0.53
    盽
    0.53
    libs
    0.52
    mesa
    0.52
    owness
    0.52
     годи
    0.52
    chessboard
    0.52
    POSITIVE LOGITS
     deseo
    0.63
     बेह
    0.62
     expect
    0.61
     mathvariant
    0.61
     such
    0.58
     tint
    0.57
    禱
    0.57
     jezik
    0.57
     himself
    0.55
    訟
    0.55
    Activations Density 0.000%

    No Known Activations