© 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. 251696
    Prev
    Next
    INDEX
    Explanations

    immediate context / edition / condition

    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
    do
    0.54
    ני
    0.49
    ﻤ
    0.47
    বাংলার
    0.47
     partake
    0.46
    giờ
    0.46
    ਲ
    0.46
    未能
    0.46
    문
    0.46
    مم
    0.46
    POSITIVE LOGITS
     Alkohol
    0.50
     Acids
    0.49
     vielä
    0.49
     Digestive
    0.48
     Temperaturen
    0.48
     MHC
    0.47
     verfü
    0.47
     Temperatur
    0.47
     Wizards
    0.47
     Reakt
    0.47
    Activations Density 0.000%

    No Known Activations