© 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. 22-GEMMASCOPE-RES-131K
    7. 98550
    Prev
    Next
    INDEX
    Explanations

    people's names and titles

    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_22/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
    u
    -1.00
    il
    -0.94
    umers
    -0.93
    у
    -0.90
    ica
    -0.88
    
    -0.88
    ji
    -0.86
    im
    -0.85
    и
    -0.84
    ï
    -0.84
    POSITIVE LOGITS
    我们的
    1.19
     naszych
    0.97
    Vá
    0.97
    Preparazione
    0.95
     testé
    0.94
     Hæ
    0.94
    我們的
    0.92
    ായി
    0.90
     разных
    0.89
     հղումներ
    0.89
    Activations Density 0.023%

    No Known Activations