© 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-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 14135
    Prev
    Next
    INDEX
    Explanations

    greater than

    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
     ప్రజ
    0.29
     Attractions
    0.29
    坟
    0.29
     سرزمین
    0.27
    昶
    0.27
    ُمْ
    0.27
     мяс
    0.26
     conoscenze
    0.26
    LING
    0.26
     здесь
    0.26
    POSITIVE LOGITS
     बहि
    0.31
    ()?>
    0.29
    7
    0.29
    nahi
    0.29
    9
    0.29
    relevant
    0.28
    azir
    0.28
    रील
    0.28
    8
    0.28
     relevant
    0.27
    Activations Density 0.035%

    No Known Activations