© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91653
    Prev
    Next
    INDEX
    Explanations

    thankful and grateful

    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
    confidence
    -0.85
    류
    -0.83
     informacion
    -0.82
     snippetHide
    -0.79
     parseFloat
    -0.78
     mempelajari
    -0.76
    极了
    -0.75
     información
    -0.74
     humano
    -0.73
     tolu
    -0.73
    POSITIVE LOGITS
     thankful
    2.52
     grateful
    2.48
     gratitude
    2.45
     Gratitude
    1.85
     ungrateful
    1.78
     appreciate
    1.72
     blessings
    1.66
     appreciation
    1.66
     agradec
    1.56
     Grateful
    1.54
    Activations Density 0.026%

    No Known Activations