© 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
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 6820
    Prev
    Next
    INDEX
    Explanations

    confidentiality and secrecy

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

    confidentiality and secrecy

    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
     flatten
    0.42
     flattening
    0.38
     flattened
    0.36
    uales
    0.35
     ٹک
    0.35
    辙
    0.35
    趄
    0.35
    幡
    0.35
     infinit
    0.35
    倬
    0.35
    POSITIVE LOGITS
     confidential
    3.42
     secrecy
    3.31
     secret
    3.25
    秘密
    3.22
     confidentiality
    3.08
     secretive
    3.02
     비밀
    3.02
     Confidential
    3.00
    secret
    2.98
     गोपनीय
    2.95
    Activations Density 0.282%

    No Known Activations