© 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. 40-GEMMASCOPE-2-RES-262K
    7. 222920
    Prev
    Next
    INDEX
    Explanations

    high quality, level, or abstract concepts

    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_40_width_262k_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
     Doppel
    0.44
     машинасы
    0.43
     Rival
    0.42
     करिए
    0.41
    ुए
    0.39
     suitcase
    0.38
     ㅣ
    0.38
    公平
    0.38
    强的
    0.38
    жди
    0.38
    POSITIVE LOGITS
     lofty
    0.74
    highest
    0.73
     elevated
    0.70
     exalted
    0.70
     highest
    0.67
     loft
    0.65
    elev
    0.64
    Highest
    0.64
     elevating
    0.63
     higher
    0.63
    Activations Density 0.024%

    No Known Activations