© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 48067
    Prev
    Next
    INDEX
    Explanations

    possessive determiners followed by nouns

    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_34/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
     itself
    -1.27
     себя
    -1.22
    ตัวเอง
    -1.21
     herself
    -1.20
    自己
    -1.19
     sendiri
    -1.13
     oneself
    -1.10
     própria
    -1.09
     own
    -1.09
     themselves
    -1.07
    POSITIVE LOGITS
     footsteps
    1.09
     wavelength
    1.06
     presence
    1.05
     weaknesses
    1.02
     mistakes
    1.01
     stuff
    1.00
    alogie
    0.95
     ideas
    0.93
     behalf
    0.92
     praises
    0.91
    Activations Density 0.048%

    No Known Activations