© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 12942
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by definite articles

    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
    ,
    -1.17
     häufiger
    -1.07
    '
    -0.96
    ticoli
    -0.96
     hinsichtlich
    -0.95
    惆
    -0.93
    ются
    -0.93
     ständig
    -0.93
    umpy
    -0.93
     więc
    -0.92
    POSITIVE LOGITS
     its
    2.14
     itself
    1.85
     memudahkan
    1.30
     kepentingan
    1.23
     keperluan
    1.20
     оно
    1.19
     محفوظة
    1.13
     diperlukan
    1.12
    ność
    1.10
     stessi
    1.10
    Activations Density 0.099%

    No Known Activations