© 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. 34-GEMMASCOPE-RES-131K
    7. 65751
    Prev
    Next
    INDEX
    Explanations

    preposition with

    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_34/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
    だが
    -1.41
    &
    -1.23
     奶油
    -1.23
    があります
    -1.21
     його
    -1.20
     perfección
    -1.19
    čnosti
    -1.18
    濠
    -1.16
     使っ
    -1.15
    因为他
    -1.15
    POSITIVE LOGITS
     regard
    2.16
     regards
    2.14
     no
    2.06
     minimal
    1.98
     a
    1.88
     little
    1.86
     impunity
    1.77
     some
    1.73
     respect
    1.66
    うわ
    1.66
    Activations Density 0.154%

    No Known Activations