© 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. 4478
    Prev
    Next
    INDEX
    Explanations

    few options for people

    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
     type
    0.44
    Type
    0.39
     Jenis
    0.37
    ↵
    0.36
     parameter
    0.35
    Jenis
    0.34
     jenis
    0.33
    特定
    0.33
    ĭ
    0.33
     existing
    0.33
    POSITIVE LOGITS
     люди
    0.45
     pessoas
    0.44
     clientes
    0.43
     fois
    0.42
     ennemis
    0.42
     colegas
    0.41
     amigas
    0.41
     ludzie
    0.41
     mensen
    0.39
     huesos
    0.39
    Activations Density 0.110%

    No Known Activations