© 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. 127861
    Prev
    Next
    INDEX
    Explanations

    foreign language results

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

    I'm not saying X, but Y

    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
    ্যাল
    0.54
    害怕
    0.49
    胼
    0.48
    秉
    0.43
    цата
    0.43
    abor
    0.42
     शुरूआत
    0.42
    wid
    0.42
    踝
    0.42
    头
    0.42
    POSITIVE LOGITS
     sonuç
    0.56
     入れ
    0.56
     RESULTS
    0.55
     прожи
    0.55
     risultati
    0.52
     ヨ
    0.52
     เก
    0.51
     இதன்
    0.51
     дов
    0.51
     результаты
    0.50
    Activations Density 0.000%

    No Known Activations