© 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. 10-GEMMASCOPE-RES-131K
    7. 65575
    Prev
    Next
    INDEX
    Explanations

    subjective feelings and states

    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_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
    Ꭻ
    -1.74
     artísticas
    -1.70
     the
    -1.70
    ꨄ
    -1.63
    VERTISEMENT
    -1.63
    送给
    -1.61
     energético
    -1.58
    
    -1.58
     выборе
    -1.55
     thirteen
    -1.55
    POSITIVE LOGITS
    {
    2.00
    “
    2.00
    1
    1.83
    8
    1.83
     unſ
    1.82
    7
    1.77
    4
    1.62
     вещи
    1.62
     hjär
    1.55
    一种
    1.54
    Activations Density 0.002%

    No Known Activations