© 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. 21146
    Prev
    Next
    INDEX
    Explanations

    gonna followed by a verb

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

    The neuron activates on the informal future-tense marker “gonna.”

    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
    」
    -2.63
     pesky
    -2.33
    ="
    -2.27
    。
    -2.25
    
    -2.22
     близ
    -2.19
    w
    -2.19
     Warszawie
    -2.17
    }\
    -2.16
     pinnacle
    -2.13
    POSITIVE LOGITS
    
    2.16
    
    2.13
     It
    2.11
    ↵
    1.98
     pronom
    1.91
     北市
    1.88
    棡
    1.87
    攫
    1.84
     Antônio
    1.84
    er
    1.84
    Activations Density 0.001%

    No Known Activations