© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 1418
    Prev
    Next
    INDEX
    Explanations

    emission standards, sea explorer

    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
     appunto
    0.36
    ។
    0.30
     però
    0.29
     wretched
    0.29
    .
    0.28
     oben
    0.28
    كي
    0.27
     erhe
    0.27
     incluso
    0.27
     the
    0.27
    POSITIVE LOGITS
    ম্বা
    0.31
    或
    0.30
     newsletters
    0.29
     অথবা
    0.29
    由
    0.28
     или
    0.27
     στην
    0.27
    थरूम
    0.27
     లేదా
    0.26
     спорт
    0.25
    Activations Density 1.821%

    No Known Activations