© 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. 10-GEMMASCOPE-RES-131K
    7. 85151
    Prev
    Next
    INDEX
    Explanations

    the [noun]

    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_10/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
     dekoratif
    -2.03
     diki
    -2.03
     Национальный
    -2.02
     للاس
    -1.87
    "{\
    -1.84
     hırka
    -1.81
     kemer
    -1.78
     kollu
    -1.77
     kapak
    -1.76
    非常好
    -1.76
    POSITIVE LOGITS
    を読む
    1.88
    .}(
    1.59
     specifically
    1.55
     namelijk
    1.53
    を読
    1.52
    を買う
    1.52
    葙
    1.52
    を知る
    1.52
    摇了
    1.48
     making
    1.47
    Activations Density 0.072%

    No Known Activations