© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 16113
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns followed by nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    灞
    0.90
     externalities
    0.87
     दिनों
    0.84
    üş
    0.83
     abnormalities
    0.82
    тэй
    0.82
    𝙲
    0.81
     enfermedades
    0.81
     kişiler
    0.81
    t
    0.81
    POSITIVE LOGITS
    5
    1.33
    2
    1.27
    6
    1.14
    7
    1.14
    9
    1.09
    4
    1.09
    1
    1.07
    8
    1.03
    EN
    1.00
    3
    0.99
    Activations Density 0.081%

    No Known Activations