© 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. 58324
    Prev
    Next
    INDEX
    Explanations

    reply.com or //

    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
     چسب
    -0.82
     radically
    -0.80
     climbing
    -0.80
    มากกว่า
    -0.79
    Dik
    -0.79
     instantly
    -0.78
     Ibid
    -0.77
     реки
    -0.77
     immediately
    -0.76
     swiftly
    -0.76
    POSITIVE LOGITS
    zmán
    0.88
     também
    0.85
    ord
    0.82
    joins
    0.82
    ');
    0.82
    illä
    0.80
    ni
    0.79
     به‌
    0.79
    บน
    0.79
    zas
    0.79
    Activations Density 0.001%

    No Known Activations