© 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. 10-GEMMASCOPE-RES-131K
    7. 9837
    Prev
    Next
    INDEX
    Explanations

    verb followed by preposition or object

    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
    ︕
    -1.57
    竟然是
    -1.57
     durab
    -1.40
    又是一
    -1.40
    ៗ
    -1.39
    yskland
    -1.39
     Tämä
    -1.37
    ۰۰
    -1.35
     atau
    -1.35
     في
    -1.35
    POSITIVE LOGITS
     [
    1.77
     
    1.68
     his
    1.59
    [
    1.44
     then
    1.36
    (
    1.36
     him
    1.34
     (
    1.30
    :
    1.29
     her
    1.28
    Activations Density 0.330%

    No Known Activations