© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47853
    Prev
    Next
    INDEX
    Explanations

    click here links

    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
    cuela
    -0.92
     продолжает
    -0.88
     deoarece
    -0.88
    九年
    -0.87
     also
    -0.86
     arbeits
    -0.83
    八年
    -0.82
     In
    -0.82
     Prinzip
    -0.81
    ultado
    -0.79
    POSITIVE LOGITS
     HERE
    3.63
     here
    3.16
    HERE
    2.80
    here
    2.25
     aquí
    2.19
     aqui
    1.91
     هنا
    1.89
     здесь
    1.70
     här
    1.69
    在这里
    1.67
    Activations Density 0.079%

    No Known Activations