© 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-262K
    7. 123096
    Prev
    Next
    INDEX
    Explanations

    explaining methods and 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_31_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
    ตาย
    0.44
     ตาย
    0.43
     ভয়াবহ
    0.42
    祓
    0.42
    ikaze
    0.41
     쉽게
    0.41
    Estimate
    0.41
     อืม
    0.41
     숙
    0.41
     Landau
    0.40
    POSITIVE LOGITS
     for
    0.55
     showcasing
    0.54
     with
    0.52
     smartwatch
    0.51
     fintech
    0.50
     arbitrage
    0.50
     that
    0.50
     biometric
    0.50
     monetize
    0.50
     neurom
    0.49
    Activations Density 0.001%

    No Known Activations