© 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. 34-GEMMASCOPE-RES-131K
    7. 75519
    Prev
    Next
    INDEX
    Explanations

    software licenses and testing methods

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

    The neuron specifically fires on occurrences of the verb “receive,” especially in method‐call contexts (e.g. allow…to receive, expect…to receive).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     tức
    -0.71
     ダウン
    -0.68
     برق
    -0.67
    composición
    -0.64
     crocodile
    -0.63
    ButtonPressed
    -0.62
     した
    -0.61
    indeed
    -0.60
    仔
    -0.60
    Amerika
    -0.60
    POSITIVE LOGITS
    gono
    0.79
    raad
    0.72
     Astronomy
    0.71
     pala
    0.71
    mehl
    0.69
     Wetter
    0.69
    工资
    0.68
    的问
    0.68
     norms
    0.67
    onts
    0.67
    Activations Density 0.061%

    No Known Activations