© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 15389
    Prev
    Next
    INDEX
    Explanations

    possession using possessive pronouns and "own"

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

    possessive with "own"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     relacionamento
    0.44
     destino
    0.41
     отношению
    0.41
    日益
    0.41
     saraf
    0.40
     comportamiento
    0.39
    兒子
    0.39
    孱
    0.39
    കള
    0.39
     Almeida
    0.39
    POSITIVE LOGITS
     propias
    0.53
    Own
    0.49
    0
    0.49
     own
    0.48
    own
    0.48
     Own
    0.48
     OWN
    0.45
    1
    0.44
     propres
    0.44
    G
    0.44
    Activations Density 0.225%

    No Known Activations