© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 49412
    Prev
    Next
    INDEX
    Explanations

    compression and support

    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_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
     entendimento
    0.43
     চুক্তি
    0.39
    नेता
    0.39
    コンサート
    0.39
    讨
    0.39
    踮
    0.38
    носи
    0.37
    തന്ത്ര
    0.37
    诨
    0.37
     suburban
    0.37
    POSITIVE LOGITS
     support
    0.86
     Support
    0.86
    Support
    0.83
     compression
    0.79
     SUPPORT
    0.79
     supports
    0.77
    サポート
    0.75
     immobilization
    0.73
     Supports
    0.72
     Compression
    0.72
    Activations Density 0.042%

    No Known Activations