© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 6513
    Prev
    Next
    INDEX
    Explanations

    mixed language punctuation

    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
     spezif
    0.35
    pecific
    0.33
     (?)
    0.33
     (%)
    0.33
     bestimmte
    0.33
     (*)
    0.31
    ின்றான்
    0.31
     پک
    0.31
     möglichen
    0.31
    :...
    0.31
    POSITIVE LOGITS
    。『
    0.46
    และ
    0.44
     แถม
    0.42
    。“
    0.41
    。
    0.41
     এবং
    0.41
     그리고
    0.40
    并且
    0.39
     hatta
    0.39
     bahkan
    0.38
    Activations Density 0.997%

    No Known Activations