© 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. 64955
    Prev
    Next
    INDEX
    Explanations

    programming code keywords

    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
     Wählen
    -1.01
     fabulous
    -0.98
     other
    -0.94
    tituto
    -0.92
    btnDelete
    -0.90
     Klicken
    -0.90
     ರ
    -0.90
     fantastic
    -0.88
    lenovo
    -0.88
    flap
    -0.88
    POSITIVE LOGITS
     Indon
    0.88
     Dá
    0.88
    Gesellschaft
    0.87
     parlar
    0.86
    껑
    0.85
     Pará
    0.85
     Juárez
    0.84
     Sør
    0.84
    şil
    0.82
     luni
    0.82
    Activations Density 0.010%

    No Known Activations