© 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. 1783
    Prev
    Next
    INDEX
    Explanations

    foreign languages and words

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

    spread out

    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
     $\
    0.34
     enhance
    0.34
    8
    0.33
     each
    0.33
     results
    0.33
     additional
    0.32
     enhances
    0.32
    6
    0.32
     expect
    0.31
     increases
    0.31
    POSITIVE LOGITS
     बेसिकली
    0.45
    私が
    0.43
     покупать
    0.41
     vreau
    0.41
    một
    0.40
     моя
    0.40
    یعنی
    0.40
    我自己
    0.39
     mío
    0.39
     একটা
    0.38
    Activations Density 0.001%

    No Known Activations