© 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. 11808
    Prev
    Next
    INDEX
    Explanations

    percentages and related words

    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
     Duct
    0.47
     Coron
    0.46
     DD
    0.46
     Ensure
    0.45
     \*
    0.44
     Power
    0.43
     Pom
    0.43
     Milk
    0.43
    旪
    0.43
    1
    0.43
    POSITIVE LOGITS
    %:
    0.73
     प्रतिशत
    0.66
     percents
    0.66
    %,
    0.66
    %.
    0.65
    percent
    0.65
     yüzde
    0.65
    %',
    0.64
     percentuale
    0.63
     процен
    0.61
    Activations Density 0.188%

    No Known Activations