© 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. 1575
    Prev
    Next
    INDEX
    Explanations

    acknowledgement confirmation receipt

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

    The neuron fires strongly on words that denote confirmations or acknowledgments (e.g. “confirmation,” “confirmations,” “acknowledgement,” “Ack”).

    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
     about
    -1.88
     mientras
    -1.73
     have
    -1.70
    ⇡
    -1.66
     столько
    -1.55
     said
    -1.53
     who
    -1.48
     also
    -1.45
     aunque
    -1.45
     justo
    -1.43
    POSITIVE LOGITS
     ОТ
    1.56
    ing
    1.56
     КУ
    1.53
     ГО
    1.52
     magasiner
    1.50
    ♪♪
    1.49
     Entrega
    1.48
     naviguant
    1.46
     剧照
    1.45
    +++++
    1.45
    Activations Density 0.020%

    No Known Activations