© 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. 1401
    Prev
    Next
    INDEX
    Explanations

    Q: or An or So or Related

    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
    влечения
    -0.95
     Apparently
    -0.93
     giornata
    -0.92
    Obviously
    -0.91
     dostup
    -0.90
     Obviously
    -0.88
    にしました
    -0.87
     貼
    -0.85
    Although
    -0.84
     Início
    -0.84
    POSITIVE LOGITS
    Branch
    0.96
    клы
    0.95
    TouchListener
    0.93
    pipeline
    0.92
    kos
    0.92
    aaa
    0.90
    isc
    0.90
    ciences
    0.88
    transition
    0.88
     continue
    0.86
    Activations Density 0.005%

    No Known Activations