© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 199768
    Prev
    Next
    INDEX
    Explanations

    various outcomes

    np_acts-logits-general · gemini-2.5-flash-lite

    precedes noun phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Veracruz
    0.57
     .{
    0.50
    arg
    0.48
    wat
    0.48
    .*\
    0.48
     Kazim
    0.46
     चौथे
    0.46
     မြ
    0.46
    ,|\
    0.46
    uiti
    0.45
    POSITIVE LOGITS
     lymphocytic
    0.48
     ciudadanía
    0.47
    ☹
    0.43
     recieved
    0.42
     quarantined
    0.41
    JSONArray
    0.41
     QTreeWidgetItem
    0.41
     conversar
    0.40
     люб
    0.40
    纳
    0.39
    Activations Density 0.001%

    No Known Activations