© 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. 4114
    Prev
    Next
    INDEX
    Explanations

    positive reception and gratitude

    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
    тически
    -0.91
    bete
    -0.78
    ńst
    -0.77
    positorio
    -0.75
    teten
    -0.74
    cuado
    -0.72
    STA
    -0.72
    carian
    -0.72
    ugian
    -0.71
    lorus
    -0.71
    POSITIVE LOGITS
     flattered
    3.38
     flattering
    2.64
     flattery
    2.14
     touched
    2.05
     humbled
    1.95
     flatter
    1.67
     overwhelmed
    1.55
     humbling
    1.52
    touched
    1.48
     touching
    1.41
    Activations Density 0.031%

    No Known Activations