© 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. 34-GEMMASCOPE-RES-131K
    7. 30055
    Prev
    Next
    INDEX
    Explanations

    return or returns

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    Negative Logits
    🤶
    -0.82
     vinaigrette
    -0.82
     رسانی
    -0.82
    ____________
    -0.80
    日记
    -0.79
    gæ
    -0.77
     recon
    -0.76
    şağı
    -0.75
    assertion
    -0.75
    bigniew
    -0.75
    POSITIVE LOGITS
    ativna
    0.83
    rtype
    0.80
    며
    0.77
     Return
    0.77
    跟
    0.76
    琅
    0.75
    ɲ
    0.75
    Literatuur
    0.74
    ᅩ
    0.73
    台上
    0.73
    Activations Density 0.029%

    No Known Activations