© 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. 44217
    Prev
    Next
    INDEX
    Explanations

    your / you

    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
     from
    -2.08
    ;
    -2.08
    ,
    -2.08
     '
    -1.91
     "
    -1.88
    “
    -1.80
     over
    -1.80
     with
    -1.70
     three
    -1.65
     one
    -1.64
    POSITIVE LOGITS
     your
    2.50
     you
    2.39
     vostre
    2.11
    İK
    1.84
    あなたの
    1.77
     it
    1.75
    怎麼
    1.75
     podemos
    1.74
    泐
    1.71
    给你
    1.67
    Activations Density 0.069%

    No Known Activations