© 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. 17-GEMMASCOPE-2-RES-16K
    7. 2068
    Prev
    Next
    INDEX
    Explanations

    javascript code blocks

    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
     моём
    1.17
     серь
    1.05
     всё
    1.03
    咱
    0.96
     মেয়ে
    0.94
     своё
    0.93
     её
    0.92
    ĝ
    0.92
     savor
    0.92
    ёр
    0.91
    POSITIVE LOGITS
     forklift
    3.02
     forkl
    2.16
     motorised
    2.01
     pallet
    1.98
     warehouse
    1.95
     lorry
    1.94
     warehousing
    1.86
     Warehouse
    1.84
     warehouses
    1.83
     HMRC
    1.76
    Activations Density 0.036%

    No Known Activations