© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 2888
    Prev
    Next
    INDEX
    Explanations

    intensifiers modifying adjectives

    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_31_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
     sâu
    0.44
     chút
    0.38
     úpl
    0.37
     égales
    0.37
     ništa
    0.37
     सबै
    0.36
    깊
    0.36
     ਜਾਂ
    0.36
     ಸ್ವಲ್ಪ
    0.35
    ubwa
    0.35
    POSITIVE LOGITS
     مهم
    0.50
    in
    0.46
     important
    0.43
     importante
    0.43
     फायदेमंद
    0.42
     permite
    0.41
    es
    0.40
     an
    0.39
    ات
    0.39
    5
    0.39
    Activations Density 0.162%

    No Known Activations