© 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. 119528
    Prev
    Next
    INDEX
    Explanations

    work for you

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

    The neuron fires on marketing-style calls to action that offer something (a tool, feature, or benefit) “to work for you” (e.g. “put … to work for you,” “tools that work for you”).

    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
     estaban
    -1.49
     детьми
    -1.43
     skrevet
    -1.34
     Schönheit
    -1.33
    整个
    -1.31
     asamblea
    -1.31
     yapılan
    -1.30
     hiasan
    -1.28
    horario
    -1.28
     mivel
    -1.27
    POSITIVE LOGITS
     our
    1.76
    沨
    1.52
    iorno
    1.48
    nemia
    1.45
     results
    1.38
    覿
    1.36
    は見
    1.36
     nocturne
    1.35
    pearance
    1.33
     CALIFORNI
    1.32
    Activations Density 0.035%

    No Known Activations