© 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. 34-GEMMASCOPE-RES-131K
    7. 92676
    Prev
    Next
    INDEX
    Explanations

    <!DOCTYPE declaration

    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
     داشتند
    -0.99
     allmäh
    -0.91
     Allemagne
    -0.90
    culin
    -0.89
    душка
    -0.85
    agé
    -0.82
    кту
    -0.81
    rotta
    -0.80
    君の
    -0.80
     Bahasa
    -0.78
    POSITIVE LOGITS
    stereotype
    1.90
    springframework
    1.34
     sorry
    1.16
     stereotype
    1.09
     stereotypes
    0.93
     Sorry
    0.89
     Ster
    0.87
     bemer
    0.86
     steroid
    0.86
    amerikanische
    0.86
    Activations Density 0.004%

    No Known Activations