© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 57071
    Prev
    Next
    INDEX
    Explanations

    theoretical others

    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
    кульп
    0.43
    SMTP
    0.43
     weaver
    0.43
    !),
    0.42
    ূতন
    0.42
    讹
    0.42
     uczest
    0.42
     octopus
    0.41
    edTest
    0.41
     jungen
    0.41
    POSITIVE LOGITS
     теорети
    0.44
     سایر
    0.44
     других
    0.42
     논
    0.42
     অন্যান্য
    0.41
     ఇతర
    0.41
     plush
    0.40
    nus
    0.40
    他の
    0.39
     другие
    0.39
    Activations Density 0.034%

    No Known Activations