© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 20754
    Prev
    Next
    INDEX
    Explanations

    how to perform actions

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

    The neuron fires on the infinitival particle “to,” particularly in “how to …” constructions.

    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
    ！！”
    -1.93
    𐐪
    -1.84
    This
    -1.80
    1
    -1.72
    不是
    -1.69
    i
    -1.69
    An
    -1.66
    この
    -1.66
    我很
    -1.66
    大量的
    -1.65
    POSITIVE LOGITS
    将她
    1.97
    搋
    1.96
    thus
    1.86
    战胜
    1.84
     esencial
    1.77
    ⚌
    1.74
    镲
    1.74
    龊
    1.72
     aspek
    1.67
    
    1.67
    Activations Density 0.046%

    No Known Activations