© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 15848
    Prev
    Next
    INDEX
    Explanations

    grayscale and black and white photography

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

    The neuron detects mentions of grayscale or monochrome image attributes (e.g. “gray,” “grayscale,” “sepia,” “monotone,” “black-and-white”).

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    -1.93
     to
    -1.83
    ?”
    -1.82
     {
    -1.76
     him
    -1.76
     This
    -1.74
     could
    -1.67
    </td>
    -1.66
     there
    -1.65
    f
    -1.65
    POSITIVE LOGITS
    －－－－
    1.70
     automóviles
    1.62
     помогает
    1.54
    ℅
    1.49
     menyen
    1.49
    ＄
    1.48
    ‼
    1.48
    Completely
    1.46
     Demokrat
    1.45
     laver
    1.44
    Activations Density 0.017%

    No Known Activations