© 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-16K
    4. 648
    Prev
    Next
    INDEX
    Explanations

    file types and identifiers

    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_16k_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
    ۔
    0.34
    。
    0.34
    Imidazole
    0.33
    сон
    0.32
    Consequently
    0.32
    ВА
    0.31
    ।
    0.31
    MyToolkit
    0.30
     hearers
    0.30
    Przyp
    0.30
    POSITIVE LOGITS
    ق
    0.52
    지
    0.51
     and
    0.50
    ید
    0.50
     not
    0.49
     I
    0.46
    jpg
    0.44
    ized
    0.43
    ج
    0.43
    T
    0.42
    Activations Density 0.561%

    No Known Activations