© 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. 100263
    Prev
    Next
    INDEX
    Explanations

    openssl commands and crypto

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

    references to OpenSSL (the cryptographic library) in text or code.

    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
    ↵
    -3.23
    e
    -2.88
     "
    -2.80
    in
    -2.75
    if
    -2.73
    ’
    -2.70
     Our
    -2.67
    o
    -2.66
    '),
    -2.63
    ...?
    -2.56
    POSITIVE LOGITS
    鷙
    2.41
    涠
    2.39
    ﱠ
    2.33
    騭
    2.33
    紅色
    2.33
     orice
    2.30
    眛
    2.25
     BIBLE
    2.22
    してない
    2.20
    情节
    2.20
    Activations Density 0.003%

    No Known Activations