© 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. 91791
    Prev
    Next
    INDEX
    Explanations

    KDE and GNU/Linux software

    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
     pulmonary
    -0.83
     SDK
    -0.83
    jorde
    -0.81
     iOS
    -0.80
    unzi
    -0.78
    ftp
    -0.78
    jpg
    -0.78
    mybatisplus
    -0.78
     "..\..\
    -0.78
     County
    -0.78
    POSITIVE LOGITS
     GN
    1.34
     Inks
    1.30
     KDE
    1.30
     GNU
    1.22
     Libre
    1.12
    tux
    1.08
    GPL
    1.05
     Fedora
    1.03
     Debian
    0.99
    Libre
    0.97
    Activations Density 0.653%

    No Known Activations