© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 60655
    Prev
    Next
    INDEX
    Explanations

    { | } , 0

    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
     förra
    -1.06
    Caracteristici
    -0.96
     just
    -0.96
    OfWeek
    -0.93
     which
    -0.91
    الدرا
    -0.88
     During
    -0.85
     disebutkan
    -0.84
    americano
    -0.84
    just
    -0.83
    POSITIVE LOGITS
    egli
    0.86
     braços
    0.84
     {...
    0.81
     الجنوب
    0.81
     оптими
    0.79
    ッタ
    0.78
     horrid
    0.76
     abusi
    0.76
    绩
    0.75
     arid
    0.75
    Activations Density 0.030%

    No Known Activations