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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7047
    Prev
    Next
    INDEX
    Explanations

    random number generation

    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
    .
    0.39
     fizer
    0.32
    g
    0.31
     devuelve
    0.31
    ,.
    0.31
    {.
    0.31
     {
    0.30
    𝗼
    0.30
     koji
    0.30
     scalar
    0.30
    POSITIVE LOGITS
     підтрим
    0.29
    менов
    0.29
    ষ্টার
    0.28
     Manajemen
    0.28
    rentes
    0.27
     আকৃষ্ট
    0.27
     найбіль
    0.27
    篾
    0.27
     اعتماد
    0.27
     mérite
    0.27
    Activations Density 0.146%

    No Known Activations