© 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
    5. 31-GEMMASCOPE-2-RES-16K
    7. 14410
    Prev
    Next
    INDEX
    Explanations

    country lists, sports teams, file systems

    np_acts-logits-general · gemini-2.5-flash-lite

    languages and geographical locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     различ
    0.41
    美丽
    0.39
     understandable
    0.38
     enam
    0.37
     StringBuffer
    0.37
    =""
    0.36
     ’’
    0.36
    evening
    0.35
    美麗
    0.35
    旌
    0.35
    POSITIVE LOGITS
    ITTER
    0.40
    ienia
    0.39
    ুস
    0.39
    冠
    0.37
    僵
    0.36
    觫
    0.36
     gennaio
    0.35
    ৫০
    0.35
    ствуют
    0.35
    வண
    0.35
    Activations Density 0.097%

    No Known Activations