© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 127752
    Prev
    Next
    INDEX
    Explanations

    pixels

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

    The neuron fires on occurrences of “pixels,” i.e. mentions of pixel-based measurements or resolutions.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    1
    -2.20
    ’,
    -2.09
     ваше
    -2.03
    ā
    -1.99
     帳
    -1.91
    溲
    -1.91
    quelize
    -1.91
    𒊹
    -1.87
    谕
    -1.86
    ?’
    -1.85
    POSITIVE LOGITS
    pixels
    2.50
    ܆
    2.28
    縢
    2.27
    n
    2.19
    菒
    2.17
    蚡
    2.13
    <bos>
    2.11
     '
    2.02
    朏
    1.99
    厹
    1.93
    Activations Density 0.001%

    No Known Activations