© 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. 119488
    Prev
    Next
    INDEX
    Explanations

    relationships between concepts

    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
     gruesome
    -1.94
    
    -1.84
     goofy
    -1.77
     decidedly
    -1.73
     boister
    -1.73
     amazingly
    -1.70
     cheio
    -1.69
    歺
    -1.69
    킁
    -1.69
     craz
    -1.67
    POSITIVE LOGITS
     before
    2.53
     at
    2.48
     or
    2.45
     as
    2.42
     in
    2.39
     during
    2.31
     because
    2.09
     while
    2.06
     when
    2.00
     on
    1.91
    Activations Density 0.311%

    No Known Activations