© 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-16K
    7. 6355
    Prev
    Next
    INDEX
    Explanations

    comparative adjectives 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_24_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
    י
    1.65
    ्स
    1.60
    ي
    1.50
    si
    1.39
    sville
    1.38
    sen
    1.32
    y
    1.29
    sız
    1.23
    ください
    1.21
    s
    1.16
    POSITIVE LOGITS
     than
    2.58
     niż
    2.17
     Than
    1.94
    Than
    1.78
     än
    1.77
    than
    1.75
     kuin
    1.73
     decât
    1.70
     než
    1.45
     THAN
    1.38
    Activations Density 0.360%

    No Known Activations