© 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. 993
    Prev
    Next
    INDEX
    Explanations

    numbers followed by years or th

    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
     Ztg
    3.01
    okatokat
    2.86
    <unused1297>
    2.86
     hubungan
    2.86
    <unused1493>
    2.85
     zarówno
    2.85
    <unused1287>
    2.85
    <unused1530>
    2.83
    .??"]
    2.82
    <unused1316>
    2.82
    POSITIVE LOGITS
    ocratic
    1.72
    aging
    1.70
    ming
    1.58
    вЂ
    1.58
    aged
    1.57
    ther
    1.55
    -
    1.55
    age
    1.54
    ft
    1.52
    ological
    1.51
    Activations Density 1.425%

    No Known Activations