© 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. 13863
    Prev
    Next
    INDEX
    Explanations

    advanced experience level

    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
    𝙣
    1.78
    𝙩
    1.75
    𝙨
    1.74
    𝙮
    1.66
    उंस
    1.63
     squeezed
    1.63
    𝙢
    1.62
     старо
    1.60
    uelo
    1.58
     envej
    1.56
    POSITIVE LOGITS
     Salam
    1.51
    HttpServlet
    1.41
    ँकि
    1.41
    Thi
    1.40
     Broadway
    1.39
     Lance
    1.38
    ऽ
    1.38
     Pike
    1.36
    auch
    1.36
     अहमदाबाद
    1.35
    Activations Density 0.054%

    No Known Activations