© 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. 102732
    Prev
    Next
    INDEX
    Explanations

    Goodbye Argentina

    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_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
    同上
    -1.88
     any
    -1.66
    啭
    -1.56
    ၟ
    -1.55
     sintomas
    -1.52
    ဴ
    -1.52
    ？（
    -1.51
     lindos
    -1.50
     veteran
    -1.50
     Why
    -1.49
    POSITIVE LOGITS
    1
    1.79
     BRING
    1.59
    -
    1.56
    0
    1.48
     ????
    1.41
     gewor
    1.40
     gebeten
    1.38
     gebracht
    1.37
     такие
    1.35
     extravag
    1.35
    Activations Density 0.002%

    No Known Activations