© 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. 189
    Prev
    Next
    INDEX
    Explanations

    you, me, him, it

    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
    It
    -2.78
    2
    -2.33
    They
    -2.31
    after
    -2.31
    This
    -2.19
    After
    -2.16
    There
    -2.14
    With
    -1.97
    If
    -1.95
    You
    -1.94
    POSITIVE LOGITS
    筇
    2.08
     zape
    1.87
     least
    1.84
     který
    1.82
    閦
    1.80
     distintas
    1.79
     cambian
    1.79
     самая
    1.78
     ofthe
    1.78
    
    1.77
    Activations Density 0.013%

    No Known Activations