© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113262
    Prev
    Next
    INDEX
    Explanations

    encrypting sensitive data

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

    references to encryption, cryptography, or encrypted data in technical contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ();
    -2.63
    ኧ
    -2.58
    .”
    -2.52
    ');
    -2.45
    킁
    -2.42
    out
    -2.41
    volved
    -2.39
    所有
    -2.36
    .'
    -2.33
    鼉
    -2.28
    POSITIVE LOGITS
    ↵
    3.11
    臜
    2.72
     motocicletas
    2.59
     剧照
    2.39
     verschillen
    2.25
    谖
    2.25
    ಞ
    2.20
     spacious
    2.19
     satisfecho
    2.17
     zincir
    2.17
    Activations Density 0.006%

    No Known Activations