© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 113246
    Prev
    Next
    INDEX
    Explanations

    receive or received

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

    This neuron specializes in spotting the verb “receive” (in any inflected form, e.g. receive, received, receives).

    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
    </h1>
    -1.52
    uxta
    -1.51
     guapo
    -1.48
     an
    -1.46
    getMenuInflater
    -1.43
    馘
    -1.43
    𓆉
    -1.42
    ſelves
    -1.41
     delicioso
    -1.41
    ں
    -1.39
    POSITIVE LOGITS
     from
    2.22
     that
    1.43
     on
    1.38
     of
    1.36
     these
    1.34
    個月
    1.34
     it
    1.30
     töd
    1.23
     sogen
    1.23
     here
    1.22
    Activations Density 0.019%

    No Known Activations