© 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. 232732
    Prev
    Next
    INDEX
    Explanations

    languages and government

    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
     alignItems
    0.49
     忄
    0.49
     }]);
    0.45
     ;,
    0.45
     dzieci
    0.45
     ©️
    0.45
     итоге
    0.45
     inning
    0.45
     位
    0.44
     শ্রো
    0.44
    POSITIVE LOGITS
    別に
    0.50
    सरकार
    0.45
     multilingual
    0.45
    нија
    0.44
    ジア
    0.43
    राज्यपाल
    0.41
     governments
    0.41
     languages
    0.41
     government
    0.41
    بینی
    0.40
    Activations Density 0.001%

    No Known Activations