© 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. 34-GEMMASCOPE-RES-131K
    7. 31797
    Prev
    Next
    INDEX
    Explanations

    previous and next navigation

    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_34/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
    SaveVideo
    -0.85
    δρ
    -0.85
     ویکی‌آمباردا
    -0.81
    obao
    -0.81
    çado
    -0.80
     redacción
    -0.76
    zeß
    -0.76
    ждая
    -0.76
    deadline
    -0.75
    第二次
    -0.75
    POSITIVE LOGITS
     previous
    2.64
     prev
    2.52
    Previous
    2.23
    prev
    2.23
     Previous
    2.22
    Prev
    2.16
     next
    2.09
    previous
    2.03
    PREV
    1.95
     Prev
    1.91
    Activations Density 0.051%

    No Known Activations