© 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. 22-GEMMASCOPE-RES-131K
    7. 9725
    Prev
    Next
    INDEX
    Explanations

    resolution and restoration

    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
     also
    -1.22
     like
    -1.07
    menjadi
    -1.00
     verschieden
    -0.97
    ствием
    -0.97
     "";
    -0.95
     mencapai
    -0.94
    曾在
    -0.93
     fällt
    -0.91
     both
    -0.91
    POSITIVE LOGITS
     but
    1.97
     eventually
    1.67
    eventually
    1.61
    Eventually
    1.45
    后来
    1.43
     gracias
    1.38
     thanks
    1.38
     بعد
    1.35
     grâce
    1.34
     grazie
    1.34
    Activations Density 0.035%

    No Known Activations