© 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. 10-GEMMASCOPE-RES-131K
    4. 11373
    Prev
    Next
    INDEX
    Explanations

    many followed by a noun

    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_10/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
     everything
    -1.51
    摀
    -1.45
    なんでも
    -1.38
    いかがでしたか
    -1.34
     eenig
    -1.33
    跸
    -1.31
    
    -1.31
    すべての
    -1.30
    妩
    -1.30
     недавно
    -1.30
    POSITIVE LOGITS
     with
    1.62
     berikutnya
    1.53
     to
    1.35
     selanjutnya
    1.33
     and
    1.33
     melahirkan
    1.30
     можно
    1.29
     of
    1.27
     on
    1.23
    Since
    1.22
    Activations Density 0.044%

    No Known Activations