© 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. 1196
    Prev
    Next
    INDEX
    Explanations

    listing conjunctions

    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
     например
    0.47
     যেমন
    0.42
     వరకు
    0.42
     zarówno
    0.41
     wśród
    0.41
    ()){
    0.40
     среди
    0.40
     mesela
    0.39
    操作系统
    0.39
     অন্যতম
    0.38
    POSITIVE LOGITS
     그리고
    0.65
     และ
    0.64
     എന്നിവ
    0.62
    そして
    0.50
     وحتى
    0.50
     आणि
    0.50
     എന്നീ
    0.50
     And
    0.49
    ،
    0.46
     și
    0.45
    Activations Density 0.573%

    No Known Activations