© 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. 128973
    Prev
    Next
    INDEX
    Explanations

    XML markup and code

    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
    を
    -2.48
     Meningkatkan
    -2.27
     Memper
    -2.20
    が
    -2.06
    1
    -1.98
    は
    -1.96
     Biaya
    -1.90
     Penggunaan
    -1.88
    但是在
    -1.87
     дола
    -1.86
    POSITIVE LOGITS
    嵛
    2.61
    孭
    2.52
     belangrijk
    2.28
    </h3>
    2.23
     estándares
    2.20
    re
    2.19
    </strong>
    2.16
     revelado
    2.11
     lanzó
    2.08
     diferite
    2.08
    Activations Density 0.003%

    No Known Activations