© 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. 5444
    Prev
    Next
    INDEX
    Explanations

    removal and elimination

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

    proactively remove

    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
    ორცი
    0.38
    晏
    0.36
     Artur
    0.36
     Maitland
    0.35
    瀕
    0.34
     الخلق
    0.33
    Versioning
    0.33
    弥
    0.33
    ੦
    0.33
     मरा
    0.32
    POSITIVE LOGITS
     removal
    4.78
     Removal
    4.59
     remove
    4.53
    removal
    4.47
    remove
    4.44
     removing
    4.44
    Removal
    4.41
     removed
    4.38
     Removing
    4.34
     Remove
    4.28
    Activations Density 0.384%

    No Known Activations