© 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. 7144
    Prev
    Next
    INDEX
    Explanations

    give or bring

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     عليك
    -0.94
     our
    -0.93
    帮你
    -0.88
     your
    -0.86
    viä
    -0.84
     phono
    -0.80
     trenes
    -0.79
    hamos
    -0.79
    Você
    -0.79
    Bạn
    -0.79
    POSITIVE LOGITS
     bring
    2.36
     give
    2.23
    Bring
    2.09
    Give
    2.09
     Bring
    2.05
     Give
    2.02
    bring
    1.81
     send
    1.77
    give
    1.73
     BRING
    1.69
    Activations Density 0.043%

    No Known Activations