© 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. 116883
    Prev
    Next
    INDEX
    Explanations

    image resolution dpi px

    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
     became
    -1.67
     becomes
    -1.67
     become
    -1.59
     becoming
    -1.40
     Become
    -1.31
     Becoming
    -1.23
    Become
    -1.23
    become
    -1.23
     Becomes
    -1.14
     становится
    -1.11
    POSITIVE LOGITS
     file
    0.97
     resolution
    0.96
     RESOLUTION
    0.94
     JPEG
    0.93
     Resolution
    0.90
    Fuji
    0.84
     JPG
    0.82
    Resolution
    0.82
     jpeg
    0.81
     files
    0.79
    Activations Density 0.018%

    No Known Activations