© 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. 10232
    Prev
    Next
    INDEX
    Explanations

    instructions or commands

    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
     Equation
    0.41
     H
    0.39
     Mais
    0.38
     Circuit
    0.38
    Η
    0.37
     Gates
    0.37
     Northwest
    0.36
     Kub
    0.36
     Sel
    0.36
     Del
    0.36
    POSITIVE LOGITS
    чиком
    0.40
    énom
    0.39
    плуа
    0.38
     पटाखों
    0.38
     बाजारों
    0.37
    ኺ
    0.37
     variété
    0.37
     tendencias
    0.37
    专属
    0.36
    ർട്ട
    0.36
    Activations Density 0.012%

    No Known Activations