© 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. 47607
    Prev
    Next
    INDEX
    Explanations

    rece/rese/reese/reco word beginnings

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

    The neuron activates on tokens containing the substring “rece” (e.g. forms of receive, receipt, reseed, or proper names like Reese).

    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
    .
    -4.31
     But
    -3.42
     have
    -2.80
     His
    -2.61
     From
    -2.61
     he
    -2.58
    );
    -2.55
     of
    -2.55
     To
    -2.55
    ikusbot
    -2.38
    POSITIVE LOGITS
    栳
    3.41
    
    3.36
    鯷
    3.03
    ཫ
    2.86
    跸
    2.84
    İstin
    2.73
    ⁧
    2.73
    ㈬
    2.66
    Leírás
    2.55
    ㍑
    2.55
    Activations Density 0.004%

    No Known Activations