© 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. 40932
    Prev
    Next
    INDEX
    Explanations

    Increased or rendering options

    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
     destined
    0.52
    jenigen
    0.44
     Arbeiten
    0.44
    тического
    0.43
     bestimm
    0.43
    Greet
    0.42
    丵
    0.42
     Johnstone
    0.41
     dessous
    0.41
    MouseButton
    0.41
    POSITIVE LOGITS
     federal
    0.45
     FEMA
    0.44
     बकरी
    0.44
     federally
    0.43
     রয়েছে
    0.42
     reporters
    0.42
     &
    0.42
     คุณ
    0.42
    (
    0.41
     nationwide
    0.41
    Activations Density 0.048%

    No Known Activations