© 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. 15186
    Prev
    Next
    INDEX
    Explanations

    many/most [followed by items]

    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
     realmente
    -1.52
     to
    -1.51
    видео
    -1.45
    ícias
    -1.45
    OrWhiteSpace
    -1.44
    攢
    -1.41
    onian
    -1.41
    пример
    -1.41
     was
    -1.37
     denen
    -1.36
    POSITIVE LOGITS
    就是这样
    1.48
     nowadays
    1.47
     joão
    1.45
     SISTEMA
    1.44
     bisous
    1.43
    ൎ
    1.41
    韡
    1.40
     insists
    1.35
     NACIONAL
    1.34
     MUNDO
    1.34
    Activations Density 0.131%

    No Known Activations