© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 99034
    Prev
    Next
    INDEX
    Explanations

    get why, get it, get me wrong

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

    The neuron strongly activates on occurrences of the word “get.”

    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
     Reſ
    -1.80
    鷸
    -1.70
    itiert
    -1.70
    Ꮼ
    -1.61
    꿩
    -1.60
     certificat
    -1.59
    ꗃ
    -1.59
     pacient
    -1.58
     Légion
    -1.57
    atação
    -1.54
    POSITIVE LOGITS
    2
    2.39
    5
    1.89
    G
    1.77
    8
    1.73
    7
    1.69
    T
    1.66
    9
    1.66
     which
    1.66
    F
    1.63
    仍在
    1.62
    Activations Density 0.022%

    No Known Activations