© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 66733
    Prev
    Next
    INDEX
    Explanations

    image manipulation and agricultural harvests

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

    The neuron activates on words about cropping or trimming images (e.g., “crop,” “cropping,” “cropped”).

    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
    да
    -2.77
    on
    -2.50
    轳
    -2.33
    \
    -2.33
    }
    -2.23
    私たち
    -2.14
     and
    -2.06
     メイン
    -2.05
     It
    -2.02
    它是
    -2.02
    POSITIVE LOGITS
     et
    2.75
    b
    2.69
     ihre
    2.44
    i
    2.41
    a
    2.39
     essere
    2.36
     crops
    2.22
     abundance
    2.11
    щита
    2.08
     millennium
    2.05
    Activations Density 0.005%

    No Known Activations