© 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. 116973
    Prev
    Next
    INDEX
    Explanations

    density and questions

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

    The neuron fires on numerical specification phrases—especially screen/display measurements (e.g. “5-inch display with a screen resolution of 480×854 pixels and a pixel density of 294 ppi”).

    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
    ntomas
    -0.74
    mW
    -0.72
    честве
    -0.72
    мно
    -0.71
     fumes
    -0.71
    ꒦
    -0.70
     economy
    -0.70
    meln
    -0.69
     למע
    -0.68
    kok
    -0.68
    POSITIVE LOGITS
     density
    1.04
     PPI
    1.02
    density
    0.96
     Density
    0.95
    PPI
    0.89
     densidad
    0.86
    Density
    0.84
    ፡
    0.78
     brightness
    0.77
     Protected
    0.75
    Activations Density 0.020%

    No Known Activations