© 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. 3602
    Prev
    Next
    INDEX
    Explanations

    where followed by descriptors

    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
     використову
    0.50
    тири
    0.47
     είναι
    0.46
    макраты
    0.42
     specialise
    0.41
     specialises
    0.40
    樾
    0.40
     megfelel
    0.40
     surpasses
    0.39
     originated
    0.39
    POSITIVE LOGITS
     (
    0.72
    ↵↵
    0.57
    (
    0.55
    ↵
    0.49
     But
    0.49
    .
    0.47
     by
    0.46
     but
    0.46
     ((
    0.46
     [
    0.46
    Activations Density 0.121%

    No Known Activations