© 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-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 23613
    Prev
    Next
    INDEX
    Explanations

    sprays and spray bottles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     বন্দী
    0.47
    垒
    0.43
     vọng
    0.42
     fetches
    0.41
     रद्द
    0.40
    谣
    0.40
     крови
    0.40
    arabangsa
    0.40
    ToRemove
    0.39
    ৌ
    0.39
    POSITIVE LOGITS
     spray
    2.13
    喷
    2.05
     Spray
    2.02
     spraying
    1.98
    噴
    1.98
     sprays
    1.91
     sprayed
    1.87
    Spray
    1.84
     sprayer
    1.81
     स्प्रे
    1.71
    Activations Density 0.010%

    No Known Activations