© 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
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 9356
    Prev
    Next
    INDEX
    Explanations

    words ending in "ence" or "tive"

    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_13_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
     жид
    1.11
    Anna
    1.10
    Elena
    1.04
     дево
    1.03
    Sheila
    1.01
     puede
    1.00
     debe
    1.00
    嶆
    1.00
    хоро
    1.00
    ktu
    0.99
    POSITIVE LOGITS
     caravans
    1.03
    濵
    0.99
     refinancing
    0.95
     refinance
    0.92
     Speakers
    0.90
    ført
    0.89
    ാലും
    0.88
    ಿಗಳ
    0.87
    最后的
    0.87
    젠
    0.87
    Activations Density 0.000%

    No Known Activations