© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 12219
    Prev
    Next
    INDEX
    Explanations

    meg, mega, egg

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

    The neuron fires on standalone proper names and brand/product terms (i.e. capitalized named entities).

    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
    зайн
    0.61
    صی
    0.56
    сты
    0.55
     choreographer
    0.55
    の発
    0.53
    সি
    0.52
    ᑭ
    0.52
    ו
    0.51
    轿
    0.51
     நம
    0.50
    POSITIVE LOGITS
     Meg
    0.86
    Meg
    0.76
     eg
    0.74
     Eg
    0.71
     Egg
    0.67
     egg
    0.65
    meg
    0.63
    Eg
    0.63
     meg
    0.63
     EG
    0.62
    Activations Density 0.145%

    No Known Activations