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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 13721
    Prev
    Next
    INDEX
    Explanations

    within the company/network

    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
    𝙩
    3.34
    𝙜
    3.28
    𝙧
    2.74
    𝖑
    2.66
    ing
    2.64
    ইংরেজি
    2.61
    ինչ
    2.55
    ensure
    2.54
    𝙠
    2.53
    िओ
    2.51
    POSITIVE LOGITS
    서
    3.54
    nya
    3.43
    了
    3.41
    다고
    3.11
    sal
    3.11
    sel
    3.06
    다는
    3.00
    ting
    3.00
    sk
    2.98
    slan
    2.84
    Activations Density 0.011%

    No Known Activations