© 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-3-12B-IT
    5. 24-GEMMASCOPE-2-RES-262K
    7. 17682
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by subjects

    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_24_width_262k_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
    రెడ్డి
    0.64
    sthe
    0.54
     применять
    0.48
     disseminated
    0.45
    <h3>
    0.45
     inherent
    0.45
    ):
    0.44
    .$\
    0.44
     occurring
    0.44
     عناصر
    0.44
    POSITIVE LOGITS
    I
    0.92
     jsem
    0.73
     Laufe
    0.72
     I
    0.71
     Ironically
    0.71
     ovaj
    0.70
     svoju
    0.68
     আমি
    0.68
     That
    0.68
     Sorry
    0.65
    Activations Density 0.002%

    No Known Activations