© 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. 117463
    Prev
    Next
    INDEX
    Explanations

    German, French, Portuguese, and English code snippets

    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
     kalın
    -0.84
    อย่างไร
    -0.84
    eably
    -0.82
    ökk
    -0.82
    shop
    -0.82
     karena
    -0.82
     statt
    -0.81
     Shop
    -0.81
     jerseys
    -0.81
    говари
    -0.79
    POSITIVE LOGITS
     gaun
    0.92
     bluse
    0.89
     Punct
    0.89
     conteúdos
    0.88
     betreffenden
    0.88
     porno
    0.87
     dortmund
    0.86
     gesuchten
    0.86
     époux
    0.84
     gewünschten
    0.84
    Activations Density 0.126%

    No Known Activations