© 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
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 6276
    Prev
    Next
    INDEX
    Explanations

    numbers and dates

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

    command line arguments and syntax

    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
    ၉
    0.45
    割引
    0.43
    ফটেন্যান্ট
    0.41
    ၆
    0.41
    簑
    0.41
    ^*$
    0.40
    arag
    0.40
    ៥
    0.39
    ٣
    0.39
    alupe
    0.39
    POSITIVE LOGITS
     ../
    0.54
     FormData
    0.51
     "";
    0.50
     ""`
    0.45
     dbo
    0.45
     ~/
    0.45
     NONE
    0.44
     *.
    0.44
     {}".
    0.43
     ./
    0.43
    Activations Density 0.207%

    No Known Activations