© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-1B
    3. 17-GEMMASCOPE-2-RES-16K
    4. 2175
    Prev
    Next
    INDEX
    Explanations

    surface coating painting spray

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_17_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
    囚
    1.22
    AVLNode
    1.19
    箩
    1.07
     AVLNode
    1.05
     Debt
    1.01
     debtors
    1.00
    Debt
    0.99
    Prison
    0.99
     mesenteric
    0.98
     ลํา
    0.98
    POSITIVE LOGITS
     spray
    3.06
     Spray
    3.01
    涂
    2.79
    Spray
    2.79
     paint
    2.76
     spraying
    2.67
     sprays
    2.67
    spray
    2.67
     Paint
    2.61
    塗
    2.61
    Activations Density 1.302%

    No Known Activations