© 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-262K
    7. 18768
    Prev
    Next
    INDEX
    Explanations

    describing actions, concepts, or entities

    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_262k_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
    тик
    0.53
     musste
    0.51
     stir
    0.44
     tuleb
    0.44
    สื่อ
    0.43
    ו
    0.43
    ਤ
    0.41
    ল
    0.41
    ท
    0.41
     vui
    0.41
    POSITIVE LOGITS
     تصور
    0.47
     제목
    0.47
     листа
    0.46
     cuestión
    0.46
     сово
    0.45
    主的
    0.45
    0.45
     प्रश्नावली
    0.44
     আবার
    0.44
     ممکن
    0.44
    Activations Density 0.001%

    No Known Activations