© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 19912
    Prev
    Next
    INDEX
    Explanations

    ECB mode encryption

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

    encryption and cryptography terms

    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_31_width_262k_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
    Revenue
    0.48
     пенсион
    0.46
     recaud
    0.45
    莘
    0.45
    接待
    0.45
    礦
    0.44
     राजस्व
    0.44
    鮪
    0.43
    SafeArea
    0.43
    矿
    0.43
    POSITIVE LOGITS
     encryption
    0.93
     Encryption
    0.89
     encrypt
    0.85
     Cipher
    0.81
     cipher
    0.80
     decryption
    0.78
     cryptography
    0.76
     ciphertext
    0.74
    encrypt
    0.72
     decrypt
    0.71
    Activations Density 0.024%

    No Known Activations