© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 54260
    Prev
    Next
    INDEX
    Explanations

    prepositions like "for"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     באמצעות
    -1.11
     Wirksamkeit
    -1.07
     Einfluß
    -1.07
     cubiertas
    -1.06
     silicona
    -1.06
    ↵
    -1.05
     помогает
    -1.04
     tenha
    -1.03
    ousal
    -0.99
    '])
    -0.98
    POSITIVE LOGITS
     for
    5.72
     для
    2.33
    สำหรับ
    1.80
     bagi
    1.76
    对于
    1.66
     بالنسبة
    1.66
     برای
    1.64
     both
    1.53
     für
    1.51
     pentru
    1.46
    Activations Density 0.030%

    No Known Activations