© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 5637
    Prev
    Next
    INDEX
    Explanations

    software updates and releases

    np_acts-logits-general · gemini-2.5-flash-lite

    constant development and updates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     edific
    0.42
    вори
    0.41
    金具
    0.41
     SUBSTIT
    0.40
    水分
    0.40
    択
    0.40
    起身
    0.40
    刺繍
    0.39
     juxtaposition
    0.39
    খান
    0.39
    POSITIVE LOGITS
     beta
    1.42
     Beta
    1.38
    Beta
    1.33
     updates
    1.31
     release
    1.27
     releases
    1.26
     BETA
    1.26
    アップデート
    1.25
     enhancements
    1.23
     bugs
    1.22
    Activations Density 0.369%

    No Known Activations