© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101114
    Prev
    Next
    INDEX
    Explanations

    `and` followed by an action or state

    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
    ichtete
    -1.66
     karena
    -1.63
     Japão
    -1.62
     departament
    -1.59
    because
    -1.59
    ка
    -1.55
     áreas
    -1.48
    there
    -1.47
    &
    -1.45
     lancar
    -1.43
    POSITIVE LOGITS
    こんばん
    1.66
     sustancia
    1.58
     нього
    1.55
    ꧁
    1.45
    (!__
    1.43
    ためには
    1.43
     цього
    1.43
    懂得
    1.42
    \|_{
    1.41
    不錯
    1.41
    Activations Density 0.162%

    No Known Activations