© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 28085
    Prev
    Next
    INDEX
    Explanations

    past events and actions

    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_22/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
     are
    -1.42
     for
    -1.20
    というわけで
    -1.17
    ♬
    -1.13
    Есть
    -1.13
    uoja
    -1.13
    خته
    -1.09
    作为
    -1.07
    Lời
    -1.07
     can
    -1.02
    POSITIVE LOGITS
     include
    1.57
     consisted
    1.51
     involving
    1.41
     resulted
    1.41
     includes
    1.41
     publicaciones
    1.27
     conducted
    1.27
     organizaciones
    1.27
     lasted
    1.24
     Includes
    1.23
    Activations Density 0.069%

    No Known Activations