© 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. 22-GEMMASCOPE-RES-131K
    7. 26026
    Prev
    Next
    INDEX
    Explanations

    before or recently

    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
     Sloveniji
    -0.82
     préférences
    -0.81
    Everyday
    -0.81
    将在
    -0.80
     morrer
    -0.78
    ないけど
    -0.78
    ржа
    -0.77
     acompañar
    -0.77
     bağlantılar
    -0.76
    tats
    -0.75
    POSITIVE LOGITS
     previous
    1.53
     предыду
    1.18
     last
    1.12
     before
    1.10
     recent
    1.08
     earlier
    1.06
     recently
    0.96
    Затем
    0.94
     Previous
    0.94
     preceding
    0.93
    Activations Density 0.123%

    No Known Activations