© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 33042
    Prev
    Next
    INDEX
    Explanations

    image stabilization, correction, enhancement, shift

    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
     farb
    -0.83
     locomo
    -0.83
     parche
    -0.82
    financi
    -0.81
    jā
    -0.81
    を切り
    -0.80
     hydrat
    -0.79
     FRANCIS
    -0.79
     dek
    -0.78
     Hijo
    -0.78
    POSITIVE LOGITS
     بهداشتی
    0.77
    sizePolicy
    0.75
     fruitless
    0.71
    Suppress
    0.71
    utor
    0.71
    setup
    0.71
     setting
    0.70
    сколь
    0.70
     creator
    0.69
     utilidad
    0.69
    Activations Density 0.009%

    No Known Activations