© 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
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 1780
    Prev
    Next
    INDEX
    Explanations

    cryptographic encryption codes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iovascular
    0.47
     насеко
    0.47
     تضيفلها
    0.45
    ᱹ
    0.45
    éries
    0.45
     locomotion
    0.45
    ndvi
    0.44
    欹
    0.44
    竿
    0.43
     ತ
    0.43
    POSITIVE LOGITS
     cryptographic
    2.06
     encryption
    2.03
     Encryption
    1.93
     cryptography
    1.91
     encrypt
    1.91
    加密
    1.73
    Encryption
    1.73
     encrypted
    1.70
     crypt
    1.66
    encryption
    1.63
    Activations Density 0.659%

    No Known Activations