© 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. 27566
    Prev
    Next
    INDEX
    Explanations

    found here

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

    information at specified locations

    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
    ബാ
    0.47
    Scan
    0.41
    اء
    0.40
    ್ಣ
    0.40
    ابا
    0.40
    チャンス
    0.39
     มัน
    0.39
    它
    0.39
    يان
    0.38
    Able
    0.38
    POSITIVE LOGITS
     наверное
    0.56
     прочита
    0.47
     ブラウン
    0.46
     вашем
    0.45
     रीडिंग
    0.45
     retrieved
    0.44
     वर्ल्ड
    0.43
     район
    0.42
     시작하겠습니다
    0.42
    こちらの
    0.42
    Activations Density 0.024%

    No Known Activations