© 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. 34-GEMMASCOPE-RES-131K
    7. 48735
    Prev
    Next
    INDEX
    Explanations

    importing namespaces or libraries

    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
     PROFES
    -0.91
    姈
    -0.91
     プリント
    -0.90
    jbl
    -0.90
    wohnt
    -0.90
     APPELL
    -0.88
     délais
    -0.88
     vời
    -0.86
    albeit
    -0.85
     baskılı
    -0.84
    POSITIVE LOGITS
     System
    1.63
     Microsoft
    1.28
    System
    1.19
    javax
    1.06
     javax
    1.04
     []:
    0.95
     сих
    0.89
     system
    0.88
     Einer
    0.87
    Obrázky
    0.85
    Activations Density 0.002%

    No Known Activations