© 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
    5. 31-GEMMASCOPE-2-RES-16K
    7. 15850
    Prev
    Next
    INDEX
    Explanations

    informational resources

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

    domain.com

    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_16k_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
    。
    0.42
    Enabled
    0.40
    5
    0.39
    .
    0.38
    3
    0.38
     sourced
    0.38
    6
    0.38
    8
    0.37
    赋予
    0.36
     ssize
    0.36
    POSITIVE LOGITS
    のは
    0.51
     Ио
    0.45
     День
    0.43
     борь
    0.42
    смотрите
    0.42
    的是
    0.42
     ninth
    0.42
    ແລະ
    0.42
     Иль
    0.41
     cliquant
    0.41
    Activations Density 0.020%

    No Known Activations