© 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-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 32542
    Prev
    Next
    INDEX
    Explanations

    particle ending in japanese or korean

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_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
     be
    1.54
    IT
    1.18
    EL
    1.13
    I
    1.13
    That
    1.13
     the
    1.12
     that
    1.09
     of
    1.07
    AN
    1.06
            
    1.05
    POSITIVE LOGITS
    ä
    1.38
    لای
    1.30
    し
    1.25
    ל
    1.23
    した
    1.21
    ید
    1.16
    ள்ளார்
    1.16
    していない
    1.12
    ת
    1.12
    には
    1.07
    Activations Density 0.001%

    No Known Activations