© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 49550
    Prev
    Next
    INDEX
    Explanations

    foreign languages and specific phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    รู้
    0.46
    ทั้งหมด
    0.46
    उ
    0.46
    на
    0.46
     stabile
    0.45
    export
    0.45
    ιν
    0.44
    𓍊
    0.44
    تج
    0.43
    聳
    0.43
    POSITIVE LOGITS
     نگ
    0.53
     નાના
    0.50
     یک
    0.46
     स्वतः
    0.43
    ដែលអាច
    0.43
     أو
    0.42
     શરી
    0.41
     കൃ
    0.41
     کاهش
    0.41
     ધ્યાન
    0.41
    Activations Density 0.006%

    No Known Activations