© 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. 12-GEMMASCOPE-2-RES-262K
    7. 9164
    Prev
    Next
    INDEX
    Explanations

    的 + subsequent noun

    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_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
    en
    1.70
    k
    1.59
    an
    1.48
    le
    1.37
    t
    1.35
    m
    1.32
    o
    1.30
    te
    1.27
    g
    1.27
    al
    1.27
    POSITIVE LOGITS
    ς
    1.13
     tão
    0.98
    ことが多い
    0.95
     conducive
    0.90
     chronically
    0.90
     devote
    0.89
     なっ
    0.89
     zároveň
    0.88
     thoroughly
    0.87
     لیے
    0.86
    Activations Density 0.004%

    No Known Activations