© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 65539
    Prev
    Next
    INDEX
    Explanations

    apprentice(s) and apprenticeship

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

    The neuron activates on terms related to apprenticeships and apprentice training (e.g., “apprentice,” “apprentices,” “apprenticeship,” etc.).

    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
     rechte
    -2.48
     asamblea
    -2.47
    𖤍
    -2.42
     bailarina
    -2.39
    锨
    -2.38
    僰
    -2.38
    艄
    -2.38
    畚
    -2.36
    栳
    -2.36
    "../
    -2.34
    POSITIVE LOGITS
    Although
    3.05
    While
    2.92
    Despite
    2.89
    what
    2.83
    After
    2.80
    It
    2.78
     While
    2.75
    With
    2.73
    During
    2.67
     Eight
    2.67
    Activations Density 0.003%

    No Known Activations