© 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. 963
    Prev
    Next
    INDEX
    Explanations

    running python scripts

    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
    نك
    1.81
    ن
    1.76
     бы
    1.76
    ла
    1.55
    짜
    1.51
     solid
    1.50
     solidly
    1.46
     yem
    1.46
    mok
    1.46
    윗
    1.44
    POSITIVE LOGITS
    *************
    2.12
    NSY
    2.11
     accueillir
    2.08
    \(
    2.06
    ************
    2.05
    ***********
    2.05
    sigh
    2.03
    //*
    1.98
    *********
    1.96
    $(
    1.95
    Activations Density 0.018%

    No Known Activations