© 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. 19384
    Prev
    Next
    INDEX
    Explanations

    Thai and Spanish conjunctions

    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
     vadati
    1.05
    al
    1.04
    ى
    1.03
    ie
    0.93
    もら
    0.93
    el
    0.91
    il
    0.89
    ↵
    0.89
     intervalles
    0.89
    ution
    0.88
    POSITIVE LOGITS
     to
    1.88
     at
    1.59
     the
    1.37
     and
    1.34
     of
    1.26
     was
    1.21
     a
    1.20
     be
    1.20
     و
    1.20
     is
    1.20
    Activations Density 0.043%

    No Known Activations