© 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. 127696
    Prev
    Next
    INDEX
    Explanations

    possessive 's followed by people's roles or life events

    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
     you
    -3.66
    ↵↵
    -2.84
     it
    -2.52
     It
    -2.14
     your
    -2.13
     is
    -2.02
     people
    -1.89
     If
    -1.89
     because
    -1.86
     remainder
    -1.83
    POSITIVE LOGITS
    himself
    2.00
    ܆
    1.98
    sieht
    1.95
    컹
    1.95
     faciliter
    1.94
     protéger
    1.93
    눙
    1.91
     stihl
    1.87
    peut
    1.87
     花纹
    1.84
    Activations Density 0.036%

    No Known Activations