© 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. 34-GEMMASCOPE-RES-131K
    7. 54346
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns referring to entities

    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
     его
    -1.22
     jego
    -1.17
     his
    -1.06
     jeho
    -0.99
     seiner
    -0.85
     Elektronik
    -0.84
    了他的
    -0.84
    issaient
    -0.82
    tak
    -0.79
    eable
    -0.79
    POSITIVE LOGITS
     own
    1.02
     name
    0.97
     choosing
    0.96
     followers
    0.95
     đĩa
    0.85
    rmk
    0.84
     hamburg
    0.84
     allowing
    0.84
     hånd
    0.83
    mexic
    0.82
    Activations Density 0.012%

    No Known Activations