© 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. 66432
    Prev
    Next
    INDEX
    Explanations

    year

    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
    这些
    -2.28
    </em>
    -2.14
    這些
    -2.02
     этих
    -1.76
    1
    -1.73
    these
    -1.69
     přístup
    -1.66
    8
    -1.63
    來
    -1.61
     هذه
    -1.58
    POSITIVE LOGITS
     The
    1.70
     <",
    1.64
     your
    1.64
    quelize
    1.62
    ܜ
    1.60
     recount
    1.58
     rende
    1.57
     the
    1.55
     Архиви
    1.55
     raggiung
    1.54
    Activations Density 0.012%

    No Known Activations