© 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. 57657
    Prev
    Next
    INDEX
    Explanations

    after or post

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

    post, after

    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
     وقف
    0.47
     xưa
    0.46
    積
    0.41
    积
    0.38
     முன்னே
    0.37
    beros
    0.37
    DbType
    0.37
    মত
    0.37
     современном
    0.37
    茲
    0.36
    POSITIVE LOGITS
     post
    1.48
    post
    1.36
     pós
    1.34
     пост
    1.27
     aftermath
    1.25
     після
    1.23
     afterward
    1.21
     afterwards
    1.20
     после
    1.19
     after
    1.16
    Activations Density 0.223%

    No Known Activations