© 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. 59461
    Prev
    Next
    INDEX
    Explanations

    encryption and cryptography

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ┏
    -1.66
    ',
    -1.60
    ')],
    -1.55
    ❘
    -1.52
    )
    -1.51
     maten
    -1.50
     herbes
    -1.46
    翾
    -1.45
    (
    -1.43
    [
    -1.43
    POSITIVE LOGITS
    衚
    1.72
    uttori
    1.48
    臜
    1.39
     STILL
    1.31
    ᜀ
    1.30
     TO
    1.29
    廡
    1.28
     bezw
    1.23
     first
    1.23
    TING
    1.22
    Activations Density 0.058%

    No Known Activations