© 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. 3800
    Prev
    Next
    INDEX
    Explanations

    import and export

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

    import statements

    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
     निकलते
    0.50
     निकलने
    0.47
     inscriptions
    0.44
    䇝
    0.42
     கொண்டிருக்கும்
    0.40
    骶
    0.40
     निकले
    0.38
     时
    0.38
    离开了
    0.38
    橹
    0.38
    POSITIVE LOGITS
     import
    4.16
    import
    3.94
     Import
    3.94
    Import
    3.81
     importing
    3.66
     imports
    3.52
     Importing
    3.45
     importation
    3.44
     importar
    3.39
     IMPORT
    3.38
    Activations Density 0.105%

    No Known Activations