© 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. 83174
    Prev
    Next
    INDEX
    Explanations

    predicting next word

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

    capitalizing/changes

    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
     ছিল
    0.52
    Decre
    0.47
    氐
    0.46
    唵
    0.46
    และความ
    0.45
     ήταν
    0.44
    NaOMe
    0.43
    它是
    0.43
    צה
    0.43
     棉
    0.43
    POSITIVE LOGITS
     dubai
    0.51
     fährt
    0.47
     berangkat
    0.47
     Kolkata
    0.47
     Abhishek
    0.47
    prepare
    0.46
     Prepare
    0.46
     naughty
    0.46
     produk
    0.46
     persön
    0.46
    Activations Density 0.000%

    No Known Activations