© 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. 98343
    Prev
    Next
    INDEX
    Explanations

    image width and resolution

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires most strongly on numeric literals (i.e. tokens representing numbers or dimensions).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     five
    -0.95
    俭
    -0.90
     nine
    -0.87
    اک
    -0.81
    akum
    -0.79
     seven
    -0.79
    夭
    -0.77
     first
    -0.75
     Herzen
    -0.75
    工事
    -0.75
    POSITIVE LOGITS
     resolution
    1.23
     resolución
    1.00
     width
    1.00
    resolution
    0.99
    Resolution
    0.99
     resol
    0.95
     Resolution
    0.91
     cols
    0.90
     resolutions
    0.88
     Width
    0.85
    Activations Density 0.016%

    No Known Activations