© 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. 6919
    Prev
    Next
    INDEX
    Explanations

    translation and transformation

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

    The neuron activates on numeric arguments inside “translate(…)” or similar transform/translation functions, i.e. it detects coordinate values used in translation transforms.

    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
     !!!!
    -1.77
     wonderful
    -1.69
     luscious
    -1.66
    u
    -1.66
    粜
    -1.63
     magnificent
    -1.63
     
    -1.60
    蓠
    -1.58
     gruesome
    -1.55
     fantastic
    -1.55
    POSITIVE LOGITS
     with
    1.95
    𓋼
    1.81
    谂
    1.79
     \%}$
    1.72
     through
    1.71
    इटम
    1.66
    euvres
    1.63
     sehr
    1.62
    
    1.62
     вперед
    1.61
    Activations Density 0.011%

    No Known Activations