© 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. 75850
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns referencing items

    np_acts-logits-general · gemini-2.5-flash-lite

    the presence of first- or second-person possessive pronouns (e.g. “your,” “my”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     vaše
    -1.27
     jego
    -1.13
    Người
    -1.05
    他们的
    -1.05
     naše
    -1.05
    мо
    -1.01
    人の
    -0.99
    νης
    -0.98
     его
    -0.97
     теперь
    -0.96
    POSITIVE LOGITS
     previous
    1.20
     valuable
    1.16
     every
    1.15
     another
    1.13
     each
    1.12
     sufficient
    1.09
     beloved
    1.05
     precious
    1.02
     further
    1.02
     both
    1.02
    Activations Density 0.114%

    No Known Activations