© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 128187
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and related words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     इस
    -0.07
     owners
    -0.07
     people
    -0.06
    쌔
    -0.06
    setIs
    -0.06
     ಯ
    -0.06
     ppl
    -0.06
     weaker
    -0.06
    पक
    -0.05
     members
    -0.05
    POSITIVE LOGITS
     അവരുടെ
    0.08
     his
    0.08
     their
    0.08
     ihre
    0.07
     ihrer
    0.07
     ihren
    0.07
     их
    0.07
    他的
    0.07
     leur
    0.07
     الخدمات
    0.06
    Activations Density 0.030%

    No Known Activations