© 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. 19318
    Prev
    Next
    INDEX
    Explanations

    supervision

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

    The neuron detects occurrences of “supervision” (and its close variants) in the text.

    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
     با
    -2.53
    When
    -2.42
    With
    -2.39
    Historically
    -2.36
    Having
    -2.36
    because
    -2.34
    with
    -2.33
    он
    -2.31
     сможет
    -2.31
    Shortly
    -2.30
    POSITIVE LOGITS
    h
    2.92
    .
    2.84
    觏
    2.69
    n
    2.58
    瘸
    2.52
    这一次
    2.36
     them
    2.34
    ਗ਼
    2.33
    膈
    2.33
    {
    2.33
    Activations Density 0.004%

    No Known Activations