© 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. 40-GEMMASCOPE-2-RES-262K
    7. 4209
    Prev
    Next
    INDEX
    Explanations

    describing concepts with a colon

    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_40_width_262k_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
     Suppose
    0.27
    കളും
    0.27
    🌔
    0.26
     そして
    0.25
     तसेच
    0.24
     (‘
    0.23
    🗿
    0.23
     Moreover
    0.23
    そして
    0.23
    脚注
    0.23
    POSITIVE LOGITS
     מע
    0.25
     통한
    0.24
    淐
    0.24
     faith
    0.24
     ת
    0.23
    蒡
    0.23
     ভিন্ন
    0.23
    handling
    0.22
     ఎలాంటి
    0.22
     ذہنی
    0.22
    Activations Density 0.167%

    No Known Activations