© 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. 65586
    Prev
    Next
    INDEX
    Explanations

    giving and given

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

    The neuron consistently activates on occurrences of the root “give” in its various inflected forms (give, giving, given).

    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
    ｶ
    -1.57
     godk
    -1.48
    創意
    -1.45
     politiet
    -1.41
    (￣
    -1.40
    嘞
    -1.39
     keben
    -1.38
    ᎑
    -1.38
    Transk
    -1.38
    それ
    -1.36
    POSITIVE LOGITS
    ecznie
    1.41
     Technically
    1.34
    摀
    1.32
    躥
    1.30
    踯
    1.27
     astonishing
    1.26
     amazingly
    1.26
     philosophy
    1.26
    骉
    1.26
    years
    1.24
    Activations Density 0.025%

    No Known Activations