© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 80818
    Prev
    Next
    INDEX
    Explanations

    scale and resolution

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

    The neuron is strongly activated by numeric dimension and scale specifications (e.g. tokens like “2”, “x”, “3x”, “scale”), effectively detecting resolution or size metadata.

    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
     begyn
    -0.83
    nenie
    -0.80
    leck
    -0.80
     løpet
    -0.79
     securely
    -0.79
    Peterson
    -0.78
     ફ
    -0.77
    ronesia
    -0.77
    ToBounds
    -0.77
    铵
    -0.76
    POSITIVE LOGITS
     density
    1.35
     densities
    1.28
    density
    1.25
    device
    1.20
     retina
    1.13
     resolution
    1.09
     Density
    1.07
     device
    1.05
    resolution
    1.02
    密度
    1.02
    Activations Density 0.055%

    No Known Activations