© 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. 84540
    Prev
    Next
    INDEX
    Explanations

    value for money

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

    This neuron primarily fires on the word “value” (in phrases like “good value,” “value for money,” “value added,” 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_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
    ılı
    -0.80
    PNG
    -0.79
     Bev
    -0.77
    Whisper
    -0.73
     zodat
    -0.71
    Specific
    -0.69
     Glaub
    -0.69
     DUP
    -0.69
     líqu
    -0.67
    Kui
    -0.67
    POSITIVE LOGITS
     money
    1.66
    money
    1.26
    MONEY
    1.20
     MONEY
    1.07
    Money
    1.06
     Money
    1.06
     денег
    0.89
     деньги
    0.79
     Jenderal
    0.76
     ATTORNEY
    0.75
    Activations Density 0.029%

    No Known Activations