© 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. 41780
    Prev
    Next
    INDEX
    Explanations

    MM acronyms and abbreviations

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

    The neuron fires on the token “MM,” especially when used as an all-caps abbreviation in scientific method names (e.g. “MM/PBSA”).

    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
    </em>
    -3.45
    $
    -2.98
    <em>
    -2.70
    ↵
    -2.66
    ↵↵
    -2.58
    </h3>
    -2.53
     By
    -2.47
    It
    -2.41
     offer
    -2.27
    -
    -2.25
    POSITIVE LOGITS
    ఽ
    2.73
    Ꮴ
    2.66
    牂
    2.61
    𓆏
    2.59
    ౧
    2.58
    
    2.58
    ᕱ
    2.56
     použití
    2.55
     rych
    2.55
     projekty
    2.50
    Activations Density 0.003%

    No Known Activations