© 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-65K
    7. 17540
    Prev
    Next
    INDEX
    Explanations

    concepts and attributes

    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_65k_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
     是
    0.47
     因为
    0.47
    人气
    0.46
     Patreon
    0.43
     เคย
    0.43
     电
    0.42
    㣱
    0.42
     Empires
    0.41
     Stairs
    0.41
     作为
    0.41
    POSITIVE LOGITS
    osta
    0.54
    वण्यासाठी
    0.47
     νέα
    0.46
    лом
    0.46
    ėje
    0.46
     phytochemical
    0.45
    essentially
    0.44
    ळ्या
    0.44
    transcript
    0.44
    ὤ
    0.44
    Activations Density 0.006%

    No Known Activations