© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 106737
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by specific words

    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
     τις
    -0.91
    輩
    -0.87
     син
    -0.77
    apiVersion
    -0.73
     دخترانه
    -0.73
    सनीय
    -0.71
     utilizzando
    -0.70
    資
    -0.70
    ātu
    -0.70
    ailangan
    -0.70
    POSITIVE LOGITS
    orders
    0.76
     Scha
    0.76
     Dul
    0.75
     orders
    0.75
     Theatre
    0.73
    льності
    0.73
    inc
    0.71
    getCurrent
    0.71
     harina
    0.71
     شا
    0.71
    Activations Density 0.031%

    No Known Activations