© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 59610
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns followed by nouns

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

    Test-Driven, Modern, need for

    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_262k_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
     дія
    0.54
     люблю
    0.54
    я
    0.54
     программа
    0.52
    從小
    0.51
     obesidad
    0.51
    рена
    0.50
     анализа
    0.50
    ת
    0.49
    тика
    0.49
    POSITIVE LOGITS
     alternates
    0.50
     own
    0.49
     Representations
    0.48
     Repairs
    0.47
    own
    0.47
     Existing
    0.46
     defenses
    0.44
    关于
    0.44
    1
    0.43
    时
    0.43
    Activations Density 0.000%

    No Known Activations