© 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-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 11101
    Prev
    Next
    INDEX
    Explanations

    intent to perform action

    np_acts-logits-general · gemini-2.5-flash-lite

    ask user what to do

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    想要
    0.55
    渴望
    0.55
     yearning
    0.54
     désir
    0.53
     craving
    0.52
    อยาก
    0.52
     longing
    0.50
    盼
    0.48
     answers
    0.47
    ຕ້ອງການ
    0.47
    POSITIVE LOGITS
     emphasize
    0.46
     ensure
    0.44
     park
    0.43
     conserve
    0.42
     emphasizing
    0.42
     emphasises
    0.40
     emphasizes
    0.40
     ensured
    0.40
     preserve
    0.40
     preserved
    0.40
    Activations Density 0.136%

    No Known Activations