© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 44126
    Prev
    Next
    INDEX
    Explanations

    programming language keywords and symbols

    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
     of
    -1.53
     everything
    -1.26
     we
    -1.25
    icii
    -1.24
    diverse
    -1.20
    ciencia
    -1.19
     aldrig
    -1.19
     as
    -1.14
     yesterday
    -1.14
    chb
    -1.13
    POSITIVE LOGITS
    糴
    1.51
    
    1.39
    ！(
    1.38
    рочный
    1.32
    醅
    1.32
    Почему
    1.31
     över
    1.29
     draped
    1.27
    cję
    1.27
    Subview
    1.25
    Activations Density 0.024%

    No Known Activations