© 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. 128270
    Prev
    Next
    INDEX
    Explanations

    one... and one.

    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
    觏
    -1.47
    rechten
    -1.45
     encontrarás
    -1.44
     tendremos
    -1.42
     verhind
    -1.41
    臵
    -1.41
    戋
    -1.41
     nimmer
    -1.37
    有意思
    -1.37
    1
    -1.36
    POSITIVE LOGITS
     also
    2.05
     modifica
    1.52
     书法
    1.48
     Также
    1.41
     for
    1.37
     एवं
    1.35
    および
    1.30
    >(&
    1.30
     及
    1.30
    ꦮ
    1.30
    Activations Density 0.023%

    No Known Activations