© 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. 34-GEMMASCOPE-RES-131K
    7. 64949
    Prev
    Next
    INDEX
    Explanations

    Jesus Christ sacrifice

    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
    Not in Any Lists

    No Comments

    Negative Logits
    carros
    -0.88
     çocu
    -0.84
     seguras
    -0.81
    œuvres
    -0.81
    ȃ
    -0.77
     distinguir
    -0.77
     непло
    -0.77
     genellikle
    -0.75
    AIC
    -0.73
    discre
    -0.73
    POSITIVE LOGITS
     עבור
    1.08
     substitute
    1.03
    Substitute
    0.96
     deler
    0.86
    代わりに
    0.82
     ouv
    0.81
     payment
    0.81
     kurs
    0.80
     willingly
    0.79
     Gefühle
    0.79
    Activations Density 0.008%

    No Known Activations