© 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. 7-GEMMASCOPE-2-RES-16K
    7. 481
    Prev
    Next
    INDEX
    Explanations

    optionslist itemsbullet points

    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_7_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
    om
    1.07
    ោង
    1.05
    ных
    1.04
    beds
    1.01
     kho
    1.00
    <bos>
    1.00
    bed
    1.00
    lasm
    1.00
    ំណ
    1.00
    ет
    0.98
    POSITIVE LOGITS
    いたい
    1.22
     お知らせ
    1.14
    漃
    1.10
    ECTION
    1.09
     ব্রিগে
    1.07
     เป้า
    1.06
    お知らせ
    1.06
     Alcal
    1.06
    দু
    1.06
     ต่อ
    1.05
    Activations Density 0.076%

    No Known Activations