© 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. 10102
    Prev
    Next
    INDEX
    Explanations

    what is left or gone

    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
    “
    -3.20
    z
    -2.80
    s
    -2.78
    y
    -2.75
    \
    -2.75
     هو
    -2.53
    ta
    -2.39
    齪
    -2.20
     الموضوع
    -2.17
     свою
    -2.09
    POSITIVE LOGITS
     leaving
    2.81
     While
    2.64
     zarówno
    2.56
     Notably
    2.48
    筥
    2.41
    งิน
    2.39
     They
    2.36
     multitude
    2.34
     Each
    2.31
    
    2.31
    Activations Density 0.003%

    No Known Activations